© 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. 32590
    Prev
    Next
    INDEX
    Explanations

    game-related actions and items

    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
    +0.12
    0.7%
    481
    +0.11
    0.6%
    420
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.23
    476
    +0.11
    0.03
    393
    +0.08
    0.25
    Negative Logits
    abase
    -0.50
    .""
    -0.50
    assium
    -0.47
     respectively
    -0.47
     airs
    -0.46
    ols
    -0.45
    )."
    -0.45
    Tes
    -0.44
     Pwr
    -0.44
    pend
    -0.43
    POSITIVE LOGITS
     buckets
    0.50
    ETA
    0.47
    @#&
    0.47
    bugs
    0.45
    âĸĵ
    0.45
    blocks
    0.45
    019
    0.45
    Ö¼
    0.44
     +=
    0.43
     overhe
    0.43
    Activations Density 11.753%

    No Known Activations