© 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. 1225
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to directions or destinations

    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
    377
    +0.13
    0.6%
    584
    +0.10
    0.4%
    101
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.13
    0.03
    200
    +0.10
    0.02
    364
    +0.10
    0.02
    Negative Logits
    illon
    -0.71
    orum
    -0.70
    ancies
    -0.70
    iability
    -0.68
    TON
    -0.68
    rehens
    -0.66
    iddler
    -0.65
    ylon
    -0.61
    eria
    -0.61
     Mub
    -0.60
    POSITIVE LOGITS
     toward
    1.06
     towards
    1.02
    canon
    1.01
    butt
    0.98
     downwards
    0.90
    quarter
    0.88
    liner
    0.87
    lines
    0.79
    liners
    0.77
    lining
    0.77
    Activations Density 0.051%

    No Known Activations