© 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. 37122
    Prev
    Next
    INDEX
    Explanations

    information related to sports team rankings and game results

    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
    627
    +0.17
    0.6%
    481
    +0.17
    0.6%
    447
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.17
    -0.03
    627
    +0.17
    0.11
    127
    +0.15
    0.10
    Negative Logits
     guiName
    -1.59
    etheless
    -1.19
    [/
    -1.18
    byss
    -1.00
    SPONSORED
    -1.00
     [/
    -0.96
    ADVERTISEMENT
    -0.89
    VERTISEMENT
    -0.89
    %.
    -0.86
    uliffe
    -0.85
    POSITIVE LOGITS
    ):
    2.00
    )
    1.90
    ),"
    1.88
    )"
    1.87
    ),
    1.81
    )",
    1.75
    )'
    1.67
    )/
    1.65
    )-
    1.63
    )--
    1.61
    Activations Density 11.849%

    No Known Activations