© 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. 10394
    Prev
    Next
    INDEX
    Explanations

    personal relationships and social interactions

    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
    195
    +0.12
    0.5%
    242
    +0.10
    0.4%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.12
    0.12
    195
    +0.10
    0.04
    679
    +0.10
    0.13
    Negative Logits
    ISA
    -0.86
    士
    -0.83
    isal
    -0.82
    mb
    -0.81
    ATA
    -0.79
    Lv
    -0.79
    VIS
    -0.78
    ~~~~
    -0.78
    IR
    -0.77
    SPONSORED
    -0.77
    POSITIVE LOGITS
     publicly
    0.97
     himself
    0.94
     aloud
    0.92
     angrily
    0.86
     vehemently
    0.85
     defiant
    0.80
     passionately
    0.80
     onstage
    0.79
     voluntarily
    0.77
     sarcast
    0.76
    Activations Density 2.772%

    No Known Activations