© 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. 45834
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases and investigations

    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
    +0.39
    2.0%
    481
    +0.15
    0.8%
    503
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.39
    0.15
    627
    +0.15
    0.10
    503
    +0.10
    0.08
    Negative Logits
    advertisement
    -0.69
    uminati
    -0.68
    è¦ļéĨĴ
    -0.64
    20439
    -0.63
    Ú
    -0.59
    LEASE
    -0.58
    ãĥŁ
    -0.57
     EDITION
    -0.57
     âĢº
    -0.56
    utterstock
    -0.55
    POSITIVE LOGITS
     swore
    0.69
     himself
    0.64
     reverted
    0.64
     recalled
    0.64
     remembers
    0.62
    rod
    0.60
    lem
    0.59
    mond
    0.59
    oses
    0.58
     contemplated
    0.57
    Activations Density 7.202%

    No Known Activations