Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1226
    Prev
    Next
    INDEX
    Explanations

    financial terms and information

    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
    496
    +0.13
    0.6%
    420
    +0.11
    0.5%
    223
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.13
    743
    +0.11
    0.05
    375
    +0.10
    0.04
    Negative Logits
     staffing
    -0.84
     accountability
    -0.79
     timely
    -0.78
     unloaded
    -0.76
     deadlines
    -0.75
    paying
    -0.72
    Dispatch
    -0.72
     layoffs
    -0.71
     budgets
    -0.70
     rollout
    -0.70
    POSITIVE LOGITS
    tymology
    1.60
     slang
    1.36
     noun
    1.29
    ËĪ
    1.28
     pronunciation
    1.19
     Dictionary
    1.10
     Sanskrit
    1.06
     abbre
    1.05
     meanings
    1.05
     deriv
    1.02
    Activations Density 2.919%

    No Known Activations