© 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. 37392
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to organizations and processes

    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
    447
    +0.26
    1.2%
    481
    +0.24
    1.1%
    314
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.26
    0.04
    232
    +0.24
    0.04
    314
    +0.14
    0.01
    Negative Logits
     Wait
    -0.64
     overpowered
    -0.63
     unborn
    -0.62
     womb
    -0.62
     swim
    -0.62
     spoiled
    -0.62
     aspirin
    -0.60
     adversity
    -0.60
     comfort
    -0.60
     neurolog
    -0.60
    POSITIVE LOGITS
    ulhu
    1.22
    pter
    0.97
    ctive
    0.96
    ascript
    0.89
    enza
    0.88
    tions
    0.87
    Sys
    0.87
    entials
    0.85
    cia
    0.84
    cs
    0.84
    Activations Density 0.116%

    No Known Activations