© 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. 14060
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names of people or places

    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
    336
    +0.20
    0.6%
    187
    +0.18
    0.6%
    376
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.20
    0.06
    299
    +0.18
    0.07
    187
    +0.17
    0.06
    Negative Logits
    EStream
    -1.13
    gerald
    -0.97
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.93
    NESS
    -0.92
    DragonMagazine
    -0.91
     BALL
    -0.89
     reviewer
    -0.88
    IBLE
    -0.87
     Pengu
    -0.87
    */(
    -0.87
    POSITIVE LOGITS
    otor
    1.87
    ichael
    1.86
    obiles
    1.77
    asonic
    1.76
    useum
    1.67
    asonry
    1.67
    ortal
    1.66
    obil
    1.64
    ormon
    1.61
    otive
    1.58
    Activations Density 0.608%

    No Known Activations