© 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 EvalsExportsinterp-engineNEWAPI 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. 36358
    Prev
    Next
    INDEX
    Explanations

    various perspectives and reflections on personal experiences, preferences, and opinions

    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
    431
    +0.01
    0.5%
    583
    +0.01
    0.4%
    50
    +0.01
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.01
    0.46
    393
    +0.01
    0.37
    64
    +0.01
    -0.29
    Negative Logits
    Corp
    -0.10
    Yan
    -0.10
    wife
    -0.10
    mber
    -0.09
     externalToEVAOnly
    -0.09
     �
    -0.09
    ée
    -0.09
    nil
    -0.09
    alle
    -0.09
    Invalid
    -0.09
    POSITIVE LOGITS
    jri
    0.11
    adesh
    0.10
    ispers
    0.10
     Skills
    0.10
    stones
    0.10
     frameworks
    0.09
     antioxid
    0.09
    orthern
    0.09
     skills
    0.09
     fuzzy
    0.09
    Activations Density 15.385%

    No Known Activations