© 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. 13892
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to software development and computer tasks

    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
    393
    +0.26
    1.2%
    36
    +0.24
    1.1%
    447
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.26
    0.36
    159
    +0.24
    0.18
    393
    +0.16
    0.27
    Negative Logits
    Catal
    -0.77
    evidence
    -0.73
    olicy
    -0.72
    ":[
    -0.69
     Abortion
    -0.67
    reports
    -0.67
     arrangements
    -0.67
     Vaughan
    -0.66
    âĢİ
    -0.65
    achusetts
    -0.64
    POSITIVE LOGITS
     lot
    1.28
     bunch
    1.08
     nutshell
    1.07
    rouse
    1.03
    cknowled
    0.98
     few
    0.97
     couple
    0.92
    sexual
    0.91
     handful
    0.89
    merce
    0.88
    Activations Density 10.152%

    No Known Activations