© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 12280
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    87
    +0.28
    1.5%
    447
    +0.17
    0.9%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.10
    87
    +0.17
    -0.03
    537
    +0.10
    0.06
    Negative Logits
    }.
    -0.62
    ":"","
    -0.57
    evin
    -0.51
    ]),
    -0.51
    VIDIA
    -0.51
    etheless
    -0.50
    }\
    -0.48
    ''.
    -0.48
    )?
    -0.48
    ?".
    -0.47
    POSITIVE LOGITS
     onto
    0.60
     squarely
    0.59
     salute
    0.55
     equivalents
    0.55
     badge
    0.53
     logo
    0.53
     motto
    0.53
     separately
    0.53
     upside
    0.49
     differently
    0.49
    Activations Density 0.929%

    No Known Activations