© 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 12288
    9. 8-RES_FS12288-JB
    11. 9643
    Prev
    Next
    INDEX
    Explanations

    information related to news and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    116
    +0.10
    0.5%
    172
    +0.10
    0.4%
    23
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.10
    0.04
    298
    +0.10
    0.04
    608
    +0.09
    0.06
    Negative Logits
     aloud
    -0.70
    mate
    -0.69
     wisely
    -0.67
    adobe
    -0.65
    abase
    -0.62
    aiden
    -0.61
     afforded
    -0.61
    never
    -0.60
     Bare
    -0.60
    wana
    -0.60
    POSITIVE LOGITS
     havoc
    1.32
     uproar
    1.04
     mayhem
    0.94
     headaches
    0.91
     ripple
    0.90
     disturbance
    0.90
     stir
    0.90
     confusion
    0.89
     frenzy
    0.86
     panic
    0.86
    Activations Density 0.534%

    No Known Activations