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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36527
    Prev
    Next
    INDEX
    Explanations

    websites and contact information

    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
    640
    +0.06
    0.5%
    666
    +0.06
    0.5%
    426
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.06
    -0.17
    640
    +0.06
    0.19
    385
    +0.06
    0.11
    Negative Logits
     Establishment
    -0.45
     Sakuya
    -0.43
     Awakens
    -0.42
     Canter
    -0.40
     Borders
    -0.40
     disgu
    -0.39
     Pyramid
    -0.39
     Galile
    -0.38
     retali
    -0.37
     mism
    -0.36
    POSITIVE LOGITS
    english
    0.51
    @
    0.51
    Sports
    0.50
    mental
    0.50
    events
    0.50
    blogs
    0.49
    archives
    0.49
    photos
    0.49
    sports
    0.49
    yss
    0.47
    Activations Density 7.656%

    No Known Activations