© 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. 3899
    Prev
    Next
    INDEX
    Explanations

    actions that require some kind of skill, knowledge, or specific qualifications

    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
    1.1%
    442
    +0.10
    0.4%
    328
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.26
    0.11
    614
    +0.10
    0.03
    105
    +0.10
    0.06
    Negative Logits
     Democr
    -0.83
     Pill
    -0.71
     Brewers
    -0.66
     Skies
    -0.65
     Lowell
    -0.65
     Sounds
    -0.65
     Dism
    -0.64
     delinqu
    -0.64
    Ń·
    -0.64
    catentry
    -0.62
    POSITIVE LOGITS
    lessly
    1.14
    xus
    0.91
    nces
    0.78
    ache
    0.77
    othes
    0.74
     convincing
    0.73
    ACH
    0.70
    OTH
    0.69
     patience
    0.68
    ICLE
    0.68
    Activations Density 8.122%

    No Known Activations