© 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. 37317
    Prev
    Next
    INDEX
    Explanations

    references to significant dates and events associated with mourning or memorial activities

    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
    373
    +0.20
    0.9%
    378
    +0.10
    0.5%
    312
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.20
    0.02
    6
    +0.10
    0.01
    133
    +0.09
    0.01
    Negative Logits
    ancies
    -0.63
    /$
    -0.61
    \":
    -0.60
    oké
    -0.60
    +,
    -0.59
    £ı
    -0.59
    anian
    -0.58
    dogs
    -0.57
    acid
    -0.57
     brut
    -0.56
    POSITIVE LOGITS
     Hide
    0.79
     Reuters
    0.71
    ourage
    0.64
     REUTERS
    0.64
    pas
    0.62
     Authorities
    0.61
     Vanessa
    0.60
    entimes
    0.60
    window
    0.59
    ocent
    0.59
    Activations Density 0.018%

    No Known Activations