© 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. 31849
    Prev
    Next
    INDEX
    Explanations

    terms related to interception, such as intercept, intercepting, interception, and intercepted, especially in the context of defense, cybersecurity, and military operations

    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
    +0.14
    0.7%
    288
    +0.11
    0.6%
    178
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.25
    326
    +0.11
    0.20
    1
    +0.10
    0.10
    Negative Logits
    chn
    -0.73
    enstein
    -0.68
    estone
    -0.67
    Aid
    -0.64
    ened
    -0.63
    blood
    -0.58
    za
    -0.57
    hab
    -0.57
    unal
    -0.57
    itsch
    -0.57
    POSITIVE LOGITS
    ibles
    0.79
    ible
    0.77
    IBLE
    0.76
    ryption
    0.67
    ibly
    0.63
    ibility
    0.63
    rons
    0.63
    rypted
    0.63
    phis
    0.61
    ENTION
    0.61
    Activations Density 6.213%

    No Known Activations