© 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. 5366
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and information

    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
    746
    +0.12
    0.6%
    147
    +0.11
    0.5%
    223
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.12
    0.04
    284
    +0.11
    0.04
    373
    +0.10
    -0.02
    Negative Logits
    issance
    -0.80
    ibaba
    -0.75
    acca
    -0.72
    qua
    -0.70
    visors
    -0.69
     Schne
    -0.69
    yright
    -0.67
    verbs
    -0.67
    iets
    -0.65
    urdue
    -0.65
    POSITIVE LOGITS
    LY
    1.02
    ALS
    0.97
    AL
    0.91
    ILE
    0.84
    ING
    0.84
    ULAR
    0.83
    IAL
    0.81
    ENC
    0.77
    ALE
    0.76
    ally
    0.76
    Activations Density 0.171%

    No Known Activations