© 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 Local
    9. 6-RES_SCL-AJT
    11. 4209
    Prev
    Next
    INDEX
    Explanations

    opinions or subjective evaluations in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.26
    1.4%
    393
    +0.18
    1.0%
    267
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.26
    0.23
    159
    +0.18
    0.11
    598
    +0.10
    0.08
    Negative Logits
    ©¶æ¥µ
    -0.61
    onto
    -0.60
    ãĤ¹ãĥĪ
    -0.59
    resp
    -0.53
    agi
    -0.52
    imm
    -0.51
    oller
    -0.51
    lev
    -0.50
    KNOWN
    -0.49
    pots
    -0.49
    POSITIVE LOGITS
     week
    0.76
     article
    0.71
     latest
    0.70
     arrangement
    0.66
     month
    0.66
     year
    0.65
     discrepancy
    0.65
     Week
    0.64
     particular
    0.61
     slideshow
    0.61
    Activations Density 9.515%

    No Known Activations