© 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. 36536
    Prev
    Next
    INDEX
    Explanations

    quotes and descriptions related to personal experiences and feelings

    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
    +0.28
    1.3%
    393
    +0.11
    0.5%
    208
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.28
    0.21
    393
    +0.11
    0.33
    55
    +0.11
    0.19
    Negative Logits
     VIDEOS
    -0.66
    edi
    -0.66
    uin
    -0.65
    Pages
    -0.63
    edIn
    -0.60
     Pages
    -0.59
    Result
    -0.58
    enzie
    -0.57
     Blossom
    -0.56
     Rasm
    -0.56
    POSITIVE LOGITS
     regarded
    0.87
     able
    0.79
     fascinated
    0.78
     presumed
    0.71
     silent
    0.70
    acons
    0.67
     considered
    0.67
     viewed
    0.66
     synonymous
    0.66
     relegated
    0.66
    Activations Density 14.079%

    No Known Activations