Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45140
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to programming and system maintenance

    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
    240
    +0.13
    0.7%
    569
    +0.09
    0.4%
    183
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.13
    0.08
    183
    +0.09
    0.09
    640
    +0.09
    0.18
    Negative Logits
    holm
    -0.68
    foundland
    -0.58
    ingen
    -0.53
    idding
    -0.53
     agre
    -0.52
    luaj
    -0.52
    gian
    -0.52
    eers
    -0.52
    doms
    -0.51
     Kamp
    -0.51
    POSITIVE LOGITS
    aways
    0.99
     advantage
    0.97
     care
    0.83
     precedence
    0.77
    overs
    0.77
    away
    0.71
     heed
    0.71
     aback
    0.71
    OVER
    0.66
     precautions
    0.65
    Activations Density 8.395%

    No Known Activations