© 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. 32599
    Prev
    Next
    INDEX
    Explanations

    information related to legal proceedings, criminal activities, and international affairs

    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
    +0.26
    1.1%
    481
    +0.23
    1.0%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.35
    481
    +0.23
    0.32
    359
    +0.10
    0.16
    Negative Logits
    idth
    -0.64
     importance
    -0.64
    aneous
    -0.61
     thumbs
    -0.60
     divergence
    -0.60
    ussed
    -0.58
    athi
    -0.55
     penet
    -0.55
    pread
    -0.55
     convergence
    -0.54
    POSITIVE LOGITS
     fray
    0.92
     undet
    0.82
     via
    0.82
     illegally
    0.80
     voluntarily
    0.77
     ASAP
    0.77
     unlawfully
    0.76
     willingly
    0.74
     sooner
    0.73
     without
    0.73
    Activations Density 16.318%

    No Known Activations