© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11589
    Prev
    Next
    INDEX
    Explanations

    information related to the topic of torture, including specific incidents, methods, legal justifications, and consequences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.20
    0.8%
    453
    +0.15
    0.6%
    582
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.18
    453
    +0.15
    0.09
    516
    +0.12
    0.07
    Negative Logits
    soType
    -1.05
     Balance
    -0.96
    soDeliveryDate
    -0.82
     lender
    -0.79
     Bucc
    -0.78
    sonian
    -0.77
    uber
    -0.74
    phrine
    -0.74
    crypt
    -0.74
    reci
    -0.74
    POSITIVE LOGITS
     torture
    1.18
     dehuman
    1.13
     confinement
    0.99
     detainees
    0.97
     captives
    0.93
     brutality
    0.91
     Palestinians
    0.87
    reatment
    0.86
     prisoners
    0.86
     Rohingya
    0.85
    Activations Density 3.321%

    No Known Activations