© 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. 31800
    Prev
    Next
    INDEX
    Explanations

    phrases related to movie titles

    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
    +0.30
    1.6%
    314
    +0.09
    0.5%
    160
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.30
    0.35
    138
    +0.09
    0.33
    64
    +0.09
    -0.16
    Negative Logits
     proble
    -0.66
     condem
    -0.65
    raints
    -0.64
     tomat
    -0.61
    enegger
    -0.61
     sugg
    -0.60
     Seym
    -0.60
     metic
    -0.58
     lapt
    -0.58
     incorpor
    -0.57
    POSITIVE LOGITS
    cffffcc
    0.81
    ï¸ı
    0.75
    null
    0.72
    HQ
    0.71
    lux
    0.70
    Ther
    0.69
    lean
    0.68
    ever
    0.68
    âĶĢâĶĢ
    0.68
    STER
    0.68
    Activations Density 9.063%

    No Known Activations