© 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. 13777
    Prev
    Next
    INDEX
    Explanations

    references to issues related to public schools, educational policies, and school districts

    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
    +0.06
    0.5%
    453
    +0.05
    0.4%
    97
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.06
    0.03
    248
    +0.05
    0.05
    146
    +0.05
    0.11
    Negative Logits
    odox
    -0.42
    obin
    -0.39
    ous
    -0.39
    lihood
    -0.38
    sson
    -0.38
    azine
    -0.36
    iosity
    -0.35
    strument
    -0.35
    rim
    -0.34
    ivities
    -0.34
    POSITIVE LOGITS
    chool
    0.43
    afety
    0.42
    rict
    0.37
    mallow
    0.35
    ricting
    0.35
    ricted
    0.34
    agram
    0.34
    etsy
    0.32
    acist
    0.31
    esan
    0.31
    Activations Density 14.038%

    No Known Activations