© 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 3072
    9. 8-RES_FS3072-JB
    11. 2981
    Prev
    Next
    INDEX
    Explanations

    dollar amounts in financial contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    314
    +0.17
    0.8%
    578
    +0.11
    0.5%
    385
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.17
    0.06
    149
    +0.11
    0.06
    604
    +0.10
    0.06
    Negative Logits
     exerc
    -0.78
     Sed
    -0.73
     Tall
    -0.71
     Pend
    -0.70
     Tid
    -0.69
     Gors
    -0.69
     Reborn
    -0.68
     Vid
    -0.68
     Freed
    -0.66
     Redd
    -0.65
    POSITIVE LOGITS
    $$
    1.26
    100
    1.23
    250
    1.20
    150
    1.20
    500
    1.19
    300
    1.18
    200
    1.18
    400
    1.15
    350
    1.14
    1
    1.13
    Activations Density 0.270%

    No Known Activations