© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14195
    Prev
    Next
    INDEX
    Explanations

    activities and actions related to personal accomplishment and reflection

    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
    +0.25
    1.1%
    481
    +0.14
    0.6%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.25
    0.06
    78
    +0.14
    0.08
    360
    +0.11
    0.09
    Negative Logits
     Entered
    -1.03
    inently
    -0.73
    theless
    -0.71
     Frie
    -0.71
    Board
    -0.70
    mares
    -0.68
    Ĭ±
    -0.66
    staff
    -0.65
    azed
    -0.65
     Ner
    -0.64
    POSITIVE LOGITS
    pez
    1.06
    berman
    0.80
     wrong
    0.76
     differently
    0.76
    iotic
    0.75
    ggy
    0.73
     unconsciously
    0.72
    etting
    0.69
    ppel
    0.68
    ison
    0.68
    Activations Density 6.807%

    No Known Activations