© 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. 13652
    Prev
    Next
    INDEX
    Explanations

    references to specific names and technical terms, possibly related to scientific research

    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
    370
    +0.10
    0.5%
    430
    +0.09
    0.5%
    7
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.25
    326
    +0.09
    0.23
    99
    +0.09
    0.11
    Negative Logits
    mable
    -0.72
    tool
    -0.65
    tub
    -0.64
    TPPStreamerBot
    -0.64
    Berry
    -0.62
    mem
    -0.62
    bridge
    -0.62
    cards
    -0.62
    Wallet
    -0.61
    our
    -0.61
    POSITIVE LOGITS
    ine
    0.84
    imore
    0.83
    iffe
    0.80
    xon
    0.71
    igham
    0.70
    inian
    0.69
    chnology
    0.68
    oldemort
    0.68
    yip
    0.68
    idem
    0.67
    Activations Density 7.484%

    No Known Activations