© 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. 18504
    Prev
    Next
    INDEX
    Explanations

    phrases related to unique or atypical characteristics or behaviors

    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
    +0.38
    1.9%
    314
    +0.13
    0.6%
    266
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.38
    0.09
    504
    +0.13
    0.07
    6
    +0.10
    0.08
    Negative Logits
     incorpor
    -0.81
     mathemat
    -0.74
     ende
    -0.72
     obser
    -0.71
     controvers
    -0.70
     rundown
    -0.69
     notor
    -0.69
     contrace
    -0.68
     secretaries
    -0.67
     retrieval
    -0.65
    POSITIVE LOGITS
    ï¸ı
    1.26
    ¯
    0.91
    ï¸
    0.89
    ÃĽ
    0.87
    âĻ
    0.84
    °
    0.83
    âľ
    0.83
    #$
    0.81
    cause
    0.81
    endif
    0.81
    Activations Density 0.167%

    No Known Activations