© 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. 5308
    Prev
    Next
    INDEX
    Explanations

    events or incidents where someone or something "turns up."

    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
    603
    +0.12
    0.6%
    561
    +0.12
    0.5%
    262
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.12
    0.03
    262
    +0.12
    0.03
    561
    +0.10
    0.02
    Negative Logits
    ################################
    -0.84
    aim
    -0.76
    bj
    -0.73
    cest
    -0.73
    "]=>
    -0.73
    gments
    -0.72
    cean
    -0.72
    =]
    -0.71
    cknowled
    -0.71
    asus
    -0.69
    POSITIVE LOGITS
    minster
    0.74
    stairs
    0.73
    votes
    0.70
    laws
    0.67
    grades
    0.66
     hither
    0.65
    law
    0.63
    dates
    0.61
     favour
    0.59
    oon
    0.58
    Activations Density 0.122%

    No Known Activations