© 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. 31964
    Prev
    Next
    INDEX
    Explanations

    terms related to political, legal, and military contexts

    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
    580
    +0.12
    0.5%
    77
    +0.12
    0.5%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.19
    686
    +0.12
    0.07
    363
    +0.11
    0.12
    Negative Logits
    Loading
    -0.72
     (?,
    -0.67
    earable
    -0.66
    miss
    -0.66
    jah
    -0.65
    Newsletter
    -0.64
    Products
    -0.64
    DH
    -0.62
    emade
    -0.62
    Hub
    -0.61
    POSITIVE LOGITS
    conservancy
    0.66
     imagin
    0.66
    vironment
    0.64
    arently
    0.63
     preferably
    0.62
     notwithstanding
    0.62
     perspect
    0.62
     reckoning
    0.61
    ĸļ士
    0.61
     Nanto
    0.61
    Activations Density 17.171%

    No Known Activations