© 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. 37355
    Prev
    Next
    INDEX
    Explanations

    terms related to assistance and support in various contexts

    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
    679
    +0.12
    0.6%
    288
    +0.12
    0.5%
    253
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.12
    0.01
    424
    +0.12
    0.01
    575
    +0.11
    0.01
    Negative Logits
    nen
    -0.75
    forward
    -0.74
    Compar
    -0.73
    ls
    -0.69
    nces
    -0.69
    LINE
    -0.68
    ross
    -0.67
    iple
    -0.66
    aval
    -0.66
    bread
    -0.66
    POSITIVE LOGITS
     assistance
    0.98
     Desk
    0.85
     aid
    0.84
     Programs
    0.83
     Assistance
    0.83
     recipients
    0.81
     programs
    0.80
    enza
    0.80
     providers
    0.78
     provider
    0.76
    Activations Density 0.011%

    No Known Activations