© 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. 8118
    Prev
    Next
    INDEX
    Explanations

    power-related words and concepts

    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%
    259
    +0.12
    0.5%
    653
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.20
    0.06
    288
    +0.12
    0.07
    78
    +0.12
    0.05
    Negative Logits
    eday
    -0.93
     Von
    -0.91
    eret
    -0.89
    TAG
    -0.88
    ALK
    -0.88
    ç«
    -0.87
     Admission
    -0.83
     Taste
    -0.83
    ead
    -0.78
    sbm
    -0.77
    POSITIVE LOGITS
    houses
    1.24
     vested
    1.10
     levers
    1.09
    FUL
    1.08
    lessness
    1.06
     chords
    1.03
    stroke
    0.99
     outage
    0.97
    lifting
    0.95
     wielded
    0.93
    Activations Density 0.968%

    No Known Activations