© 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 EvalsExportsAPI 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. 12500
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict, war, or violence

    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
    239
    +0.14
    0.5%
    545
    +0.13
    0.5%
    298
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.14
    0.04
    636
    +0.13
    0.03
    526
    +0.12
    -0.01
    Negative Logits
    MN
    -0.89
    ML
    -0.88
     Cosponsors
    -0.88
     Encyclopedia
    -0.82
    adj
    -0.80
    FP
    -0.79
     AFL
    -0.78
     GW
    -0.76
     Analyst
    -0.76
    ãĤ¢ãĥ«
    -0.74
    POSITIVE LOGITS
     voic
    1.18
     undone
    1.11
    velop
    0.88
     mark
    0.88
     unprotected
    0.88
     untouched
    0.88
    rette
    0.86
     imprint
    0.86
     scars
    0.86
     bruises
    0.84
    Activations Density 0.598%

    No Known Activations