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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3983
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of normalcy and deviations from it

    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
    +0.23
    0.9%
    438
    +0.14
    0.6%
    271
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.23
    0.08
    724
    +0.14
    0.10
    699
    +0.12
    0.03
    Negative Logits
    hani
    -0.88
    iosyncr
    -0.82
    Sov
    -0.78
    haw
    -0.78
    NRS
    -0.75
    Lens
    -0.75
    otle
    -0.74
    artisan
    -0.74
    hire
    -0.73
    Winged
    -0.73
    POSITIVE LOGITS
    cy
    1.41
    ization
    1.41
    izes
    1.40
    izing
    1.36
    isation
    1.33
    ised
    1.31
    ize
    1.27
    izers
    1.27
    ized
    1.18
    ises
    1.15
    Activations Density 4.604%

    No Known Activations