© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 4898
    Prev
    Next
    INDEX
    Explanations

    references to different academic years and courses within certain educational institutions

    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
    480
    +0.43
    2.3%
    351
    +0.12
    0.6%
    378
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.43
    0.03
    176
    +0.12
    0.03
    130
    +0.11
    0.03
    Negative Logits
    20439
    -0.50
    agar
    -0.50
     supportive
    -0.46
     meaning
    -0.45
    meaning
    -0.44
     Sap
    -0.44
    press
    -0.43
    mans
    -0.43
     footing
    -0.42
     pressing
    -0.42
    POSITIVE LOGITS
    ?????-?????-
    0.68
    Appearances
    0.66
    ?????-
    0.66
    ¯¯¯¯¯¯¯¯
    0.65
    Ü
    0.65
     ..............
    0.63
    etc
    0.63
     etc
    0.62
    ãħĭ
    0.61
    """
    0.59
    Activations Density 0.372%

    No Known Activations