© 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. 41708
    Prev
    Next
    INDEX
    Explanations

    terms related to critical analysis and complex discussions

    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
    +0.34
    1.7%
    447
    +0.27
    1.4%
    87
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.34
    0.05
    480
    +0.27
    0.02
    464
    +0.16
    0.06
    Negative Logits
    umbn
    -0.63
    essage
    -0.62
    flix
    -0.61
    vertising
    -0.60
    swick
    -0.59
     helicop
    -0.59
    ij士
    -0.59
    trak
    -0.59
    iscovery
    -0.58
    onde
    -0.57
    POSITIVE LOGITS
    )?
    0.64
    ¶
    0.63
     OnePlus
    0.54
    \":
    0.54
    !),
    0.54
    ctive
    0.52
    ':
    0.52
     ;
    0.51
     ):
    0.51
     ),
    0.51
    Activations Density 0.278%

    No Known Activations