© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10206
    Prev
    Next
    INDEX
    Explanations

    phrases related to confrontation and conflict

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.15
    0.6%
    622
    +0.13
    0.5%
    526
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.08
    654
    +0.13
    0.06
    526
    +0.11
    -0.00
    Negative Logits
    ikes
    -0.92
    acht
    -0.88
    urrent
    -0.87
    erves
    -0.84
    emetery
    -0.84
    abet
    -0.83
    rug
    -0.82
    estone
    -0.81
    oiler
    -0.80
    onder
    -0.78
    POSITIVE LOGITS
     him
    0.91
     himself
    0.84
     truths
    0.83
     against
    0.82
     contradictions
    0.80
     questioning
    0.80
     them
    0.77
     anew
    0.77
     authenticity
    0.77
     sexism
    0.75
    Activations Density 1.409%

    No Known Activations