© 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. 37242
    Prev
    Next
    INDEX
    Explanations

    articles and determiners preceding nouns

    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
    36
    +0.22
    1.1%
    393
    +0.13
    0.6%
    328
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.22
    0.12
    250
    +0.13
    0.05
    328
    +0.10
    0.06
    Negative Logits
    notes
    -0.81
    coins
    -0.76
    encies
    -0.76
     Investigator
    -0.74
    ATURES
    -0.73
    Shape
    -0.72
    cair
    -0.72
    onge
    -0.71
     Acts
    -0.71
     examiner
    -0.69
    POSITIVE LOGITS
     plethora
    1.09
     bye
    1.06
     league
    1.03
     matchup
    1.03
     terrific
    1.02
     slew
    1.00
     whopping
    1.00
    venge
    1.00
     rematch
    1.00
     rookie
    0.99
    Activations Density 0.188%

    No Known Activations