© 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 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. 33471
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement activities like arrests, prosecutions, deportations, and detainment

    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
    +0.28
    1.3%
    507
    +0.12
    0.6%
    78
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.28
    0.10
    507
    +0.12
    0.14
    761
    +0.10
    0.11
    Negative Logits
     Aerospace
    -0.71
    quart
    -0.70
    raltar
    -0.69
    taboola
    -0.68
    luster
    -0.67
     spons
    -0.65
    ciplinary
    -0.64
    ãĤ´ãĥ³
    -0.63
    aston
    -0.63
    oday
    -0.62
    POSITIVE LOGITS
     him
    1.29
     someone
    1.07
     somebody
    1.02
     anyone
    0.99
     anybody
    0.98
     them
    0.96
     whoever
    0.91
     people
    0.80
     THEM
    0.80
     unsuspecting
    0.79
    Activations Density 8.483%

    No Known Activations