© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18500
    Prev
    Next
    INDEX
    Explanations

    names that are similar to well-known figures or terms that may carry controversial or sensitive associations

    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
    756
    +0.11
    0.7%
    575
    +0.09
    0.5%
    711
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.11
    0.05
    314
    +0.09
    -0.02
    711
    +0.08
    0.04
    Negative Logits
    !:
    -0.46
     spoilers
    -0.46
     Canaver
    -0.45
     Patreon
    -0.43
    DragonMagazine
    -0.41
     FANTASY
    -0.41
     Originally
    -0.41
     cautiously
    -0.41
     tattoos
    -0.40
     digitally
    -0.40
    POSITIVE LOGITS
    )).
    0.92
    ]).
    0.87
    .).
    0.81
    %).
    0.79
    ]."
    0.77
    ]),
    0.76
    )."
    0.76
    ).
    0.73
    )),
    0.71
    ));
    0.69
    Activations Density 2.096%

    No Known Activations