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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5277
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts related to accounting and business

    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
    +0.12
    0.6%
    59
    +0.10
    0.5%
    761
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.11
    326
    +0.10
    0.10
    464
    +0.09
    0.07
    Negative Logits
    fit
    -0.76
     includ
    -0.73
    berman
    -0.69
    sight
    -0.65
    bsite
    -0.60
    clud
    -0.58
     Kov
    -0.57
    mat
    -0.57
    spe
    -0.56
    undo
    -0.56
    POSITIVE LOGITS
    utical
    0.80
    enary
    0.72
    ilee
    0.72
    igion
    0.67
    anship
    0.67
    inding
    0.67
     Affairs
    0.66
    ience
    0.64
    wolves
    0.62
    ozyg
    0.62
    Activations Density 1.683%

    No Known Activations