© 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. 37343
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or means of doing something

    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
    224
    +0.11
    0.5%
    539
    +0.11
    0.5%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.11
    0.01
    539
    +0.11
    0.01
    435
    +0.10
    0.01
    Negative Logits
     nutshell
    -0.69
    ever
    -0.63
     STATS
    -0.63
     rated
    -0.62
    sha
    -0.61
     understatement
    -0.60
     coupon
    -0.60
     Birthday
    -0.60
     triv
    -0.60
     Cind
    -0.59
    POSITIVE LOGITS
    arthy
    0.73
    uilding
    0.67
    phabet
    0.67
    burse
    0.67
    istani
    0.66
    orthern
    0.64
    orthy
    0.64
    BACK
    0.63
    boats
    0.63
     safer
    0.63
    Activations Density 0.011%

    No Known Activations