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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37201
    Prev
    Next
    INDEX
    Explanations

    specific technical or product-related terms associated with various technologies and industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.37
    1.8%
    447
    +0.23
    1.1%
    481
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.37
    0.08
    575
    +0.23
    0.06
    481
    +0.15
    0.05
    Negative Logits
    76561
    -0.69
    yss
    -0.60
    inarily
    -0.58
    aples
    -0.57
    é¾įå
    -0.54
    itimate
    -0.53
    -)
    -0.52
    æ©
    -0.51
    igl
    -0.51
    itant
    -0.51
    POSITIVE LOGITS
     aka
    0.66
    âĢİ
    0.62
     which
    0.60
     featuring
    0.58
     (£
    0.55
     amidst
    0.54
     alongside
    0.54
     ($
    0.54
     (#
    0.52
     located
    0.52
    Activations Density 0.301%

    No Known Activations