© 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. 3856
    Prev
    Next
    INDEX
    Explanations

    specific locations or proper nouns

    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
    527
    +0.10
    0.6%
    546
    +0.09
    0.6%
    496
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.10
    0.03
    649
    +0.09
    0.02
    527
    +0.07
    0.02
    Negative Logits
    istical
    -0.55
    istics
    -0.53
     Kut
    -0.53
     puzz
    -0.52
    istically
    -0.51
    tenance
    -0.51
    intendent
    -0.50
    guards
    -0.50
     butterflies
    -0.50
    eering
    -0.49
    POSITIVE LOGITS
    HC
    0.71
    LD
    0.68
    RB
    0.66
    XT
    0.63
    GW
    0.62
    LR
    0.61
    DOC
    0.61
    CH
    0.61
    LIB
    0.61
    OME
    0.61
    Activations Density 0.153%

    No Known Activations