© 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. 12929
    Prev
    Next
    INDEX
    Explanations

    information on laws and regulations, especially related to health and safety

    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
    1.0%
    145
    +0.12
    0.5%
    759
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.23
    0.10
    11
    +0.12
    0.07
    57
    +0.10
    0.08
    Negative Logits
    ĪĴ
    -0.73
    ioned
    -0.72
     comrades
    -0.67
     reconc
    -0.67
     comrade
    -0.66
     continu
    -0.63
     classmate
    -0.62
    Nap
    -0.62
     penet
    -0.62
    flying
    -0.61
    POSITIVE LOGITS
     Isles
    0.97
    liga
    0.92
     Territories
    0.91
     Indies
    0.90
     illegally
    0.90
    outheastern
    0.87
     marketplace
    0.82
     Alps
    0.82
    vale
    0.77
    ADA
    0.76
    Activations Density 11.680%

    No Known Activations