© 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. 5400
    Prev
    Next
    INDEX
    Explanations

    financial and statistical data related to companies, organizations, and economic trends

    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
    651
    +0.16
    0.6%
    6
    +0.14
    0.5%
    721
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.16
    0.11
    436
    +0.14
    0.07
    609
    +0.13
    0.07
    Negative Logits
    psey
    -1.01
    anamo
    -0.99
    omething
    -0.98
    achus
    -0.97
    creen
    -0.96
    ktop
    -0.87
     zipper
    -0.87
    kef
    -0.86
     contag
    -0.84
    ategory
    -0.84
    POSITIVE LOGITS
    long
    1.31
     ago
    1.12
    book
    1.12
    nings
    1.11
    lings
    1.10
    ning
    1.05
     Ago
    1.04
     olds
    1.01
    ns
    0.97
    lies
    0.95
    Activations Density 0.836%

    No Known Activations