© 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. 31118
    Prev
    Next
    INDEX
    Explanations

    various actions related to handling and transforming JSON data, specific API-related terms, and technical details such as HTTP methods and response types

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.14
    0.7%
    651
    +0.11
    0.5%
    289
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.17
    288
    +0.11
    0.18
    651
    +0.10
    0.10
    Negative Logits
    manship
    -0.74
    itism
    -0.73
    ners
    -0.73
     Dull
    -0.71
    abilities
    -0.69
    forums
    -0.68
    mins
    -0.68
    llan
    -0.67
    isher
    -0.67
    espie
    -0.67
    POSITIVE LOGITS
     encoded
    0.88
     formatted
    0.83
     RPC
    0.81
     extracted
    0.79
     converter
    0.77
     parsed
    0.77
     JSON
    0.76
     parsing
    0.76
     parser
    0.76
     retrieved
    0.75
    Activations Density 4.958%

    No Known Activations