© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36912
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal documents and regulations

    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
    +0.21
    1.0%
    393
    +0.16
    0.8%
    690
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.36
    640
    +0.16
    0.34
    385
    +0.11
    0.22
    Negative Logits
    ashtra
    -0.74
    rimp
    -0.65
    thur
    -0.62
    pter
    -0.62
    grain
    -0.61
    rums
    -0.60
    ept
    -0.59
    dayName
    -0.59
    culosis
    -0.57
     traces
    -0.57
    POSITIVE LOGITS
     communicating
    0.65
     constructing
    0.65
     determining
    0.64
     avoiding
    0.62
     executing
    0.61
     maximizing
    0.60
     combating
    0.60
     owning
    0.60
    ĸ
    0.59
     photograp
    0.59
    Activations Density 14.779%

    No Known Activations