© 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. 37152
    Prev
    Next
    INDEX
    Explanations

    names of entities, brands, or titles related to content and technology

    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
    87
    +0.23
    1.2%
    481
    +0.19
    1.0%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.23
    0.06
    659
    +0.19
    0.04
    314
    +0.14
    0.00
    Negative Logits
     standpoint
    -0.65
     inclined
    -0.65
     wealthy
    -0.60
     insured
    -0.59
     politic
    -0.58
     ordinarily
    -0.58
    hesda
    -0.58
     industrialized
    -0.58
    )-
    -0.57
     manufacturer
    -0.56
    POSITIVE LOGITS
    Forward
    0.66
     Budd
    0.65
    2020
    0.64
    Fly
    0.64
     Mermaid
    0.63
    voy
    0.63
    izont
    0.62
    Aw
    0.61
    opia
    0.60
    odo
    0.60
    Activations Density 0.332%

    No Known Activations