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

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 35207
    Prev
    Next
    INDEX
    Explanations

    statements about probability and likelihood in various scenarios

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.12
    0.6%
    493
    +0.09
    0.4%
    674
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.37
    608
    +0.09
    0.24
    283
    +0.09
    0.01
    Negative Logits
    iband
    -0.79
    æµ
    -0.74
    andise
    -0.70
    Ú
    -0.67
    ansion
    -0.65
    illation
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
     Eug
    -0.63
    elfare
    -0.63
    ahime
    -0.63
    POSITIVE LOGITS
     forgiven
    0.72
     unlikely
    0.67
     underest
    0.64
     guessed
    0.63
     overest
    0.63
     underestimate
    0.63
     fingers
    0.62
     unsuspecting
    0.59
     shorth
    0.58
     slim
    0.56
    Activations Density 16.780%

    No Known Activations