© 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. 36700
    Prev
    Next
    INDEX
    Explanations

    words related to various subjects such as art, economics, politics, and sports

    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
    727
    +0.13
    0.5%
    543
    +0.12
    0.5%
    314
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    745
    +0.13
    -0.12
    640
    +0.12
    0.18
    373
    +0.12
    -0.17
    Negative Logits
    otle
    -0.89
     Mellon
    -0.76
     Clarkson
    -0.75
     Zucker
    -0.73
     Schultz
    -0.72
    eas
    -0.71
     Feder
    -0.71
    ept
    -0.70
     Schn
    -0.70
    ittered
    -0.69
    POSITIVE LOGITS
    geon
    1.52
    geons
    1.49
     Rahman
    1.16
    thur
    1.16
    andom
    1.15
    rences
    1.11
    ricular
    1.04
    anium
    1.02
    geoning
    1.00
    rr
    0.99
    Activations Density 9.339%

    No Known Activations