© 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. 37198
    Prev
    Next
    INDEX
    Explanations

    topics related to politics, economics, and regulations

    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
    288
    +0.14
    0.6%
    481
    +0.11
    0.5%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.06
    450
    +0.11
    0.03
    398
    +0.11
    0.03
    Negative Logits
    lda
    -0.82
    inia
    -0.81
    shall
    -0.76
    renheit
    -0.74
    Lago
    -0.73
    alin
    -0.73
    ptives
    -0.71
    bsp
    -0.71
    alone
    -0.69
    IDA
    -0.68
    POSITIVE LOGITS
     ramifications
    1.31
     implications
    1.27
     aspect
    1.24
     consequences
    1.21
     process
    1.17
     complexities
    1.11
     equivalent
    1.11
     implication
    1.10
     rationale
    1.10
     basis
    1.09
    Activations Density 0.119%

    No Known Activations