© 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. 3839
    Prev
    Next
    INDEX
    Explanations

    legal and judicial terms, including court cases and legal procedures

    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
    +0.22
    0.9%
    749
    +0.17
    0.7%
    567
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.22
    0.28
    107
    +0.17
    0.08
    314
    +0.11
    -0.09
    Negative Logits
     hosting
    -0.79
     imperson
    -0.74
     shrouded
    -0.71
     broom
    -0.70
     patrolling
    -0.70
     lur
    -0.70
     liking
    -0.70
     contracted
    -0.69
     composing
    -0.69
     moniker
    -0.68
    POSITIVE LOGITS
     supra
    1.49
     ¶
    1.03
     Ibid
    1.02
     pp
    0.98
     §
    0.98
    bid
    0.97
     Brief
    0.97
     §§
    0.96
    Footnote
    0.95
     Agric
    0.95
    Activations Density 23.185%

    No Known Activations