© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 46051
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to courts and court-related activities

    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
    +0.15
    0.7%
    314
    +0.13
    0.6%
    297
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.23
    6
    +0.13
    0.14
    611
    +0.12
    0.13
    Negative Logits
    ãĤ£
    -0.82
    ãĤ¤ãĥĪ
    -0.78
    yip
    -0.74
    achev
    -0.72
     veins
    -0.71
     contrace
    -0.69
    γ
    -0.65
    chieve
    -0.64
    ubi
    -0.63
    vell
    -0.62
    POSITIVE LOGITS
     Appeals
    0.96
     jurisdiction
    0.82
     Justice
    0.80
     Ober
    0.74
     Inquiry
    0.73
     Opinion
    0.70
    order
    0.70
    merce
    0.69
    sted
    0.68
    ordered
    0.67
    Activations Density 10.033%

    No Known Activations