© 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. 36220
    Prev
    Next
    INDEX
    Explanations

    discussions related to science fiction and fantasy genres, possibly involving specific aspects like characters, themes, and adaptations

    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
    314
    +0.13
    0.7%
    537
    +0.12
    0.6%
    640
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.13
    0.28
    640
    +0.12
    0.29
    102
    +0.11
    0.21
    Negative Logits
     Burr
    -0.67
     Dia
    -0.64
     Lowry
    -0.60
     Alban
    -0.60
     Holt
    -0.59
     Spo
    -0.58
     Lumpur
    -0.58
     Hels
    -0.56
     continents
    -0.56
     Rivers
    -0.56
    POSITIVE LOGITS
    style
    1.03
    based
    0.99
    driven
    0.96
    inspired
    0.96
    themed
    0.95
    related
    0.94
    derived
    0.94
    school
    0.93
    induced
    0.91
    enforcement
    0.90
    Activations Density 11.183%

    No Known Activations