© 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. 85
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly the name "Graham" in various contexts

    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
    377
    +0.22
    0.8%
    508
    +0.13
    0.5%
    683
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.22
    0.13
    288
    +0.13
    0.17
    326
    +0.13
    0.15
    Negative Logits
    letal
    -1.17
    uana
    -1.14
    odied
    -0.98
    tymology
    -0.97
    aution
    -0.96
    acter
    -0.92
     skelet
    -0.92
    hovah
    -0.92
    uo
    -0.90
    reon
    -0.90
    POSITIVE LOGITS
    keeper
    1.21
    keepers
    1.06
     Winchester
    1.02
    iversary
    1.01
    quist
    0.95
     Wass
    0.94
    coe
    0.92
    forth
    0.87
     Schmidt
    0.85
    lees
    0.85
    Activations Density 3.188%

    No Known Activations