© 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
    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. 3792
    Prev
    Next
    INDEX
    Explanations

    subscription-related information and prompts for interaction on online platforms

    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
    530
    +0.10
    0.5%
    218
    +0.10
    0.5%
    246
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.24
    6
    +0.10
    0.15
    74
    +0.09
    0.09
    Negative Logits
    isma
    -0.68
    manship
    -0.65
    perty
    -0.63
    elvet
    -0.61
     yarn
    -0.60
    ufact
    -0.59
    '-
    -0.57
     Learns
    -0.57
    ursday
    -0.56
     calf
    -0.56
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.67
    Privacy
    0.66
     iTunes
    0.65
     VIDEOS
    0.64
    ById
    0.64
    ãĥĢ
    0.62
     ARTICLE
    0.60
     gallery
    0.60
    paren
    0.60
    arger
    0.59
    Activations Density 9.997%

    No Known Activations