© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    legal or financial terms related to business and transactions

    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
    373
    +0.18
    0.9%
    209
    +0.10
    0.5%
    394
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.18
    0.04
    288
    +0.10
    0.07
    556
    +0.10
    0.04
    Negative Logits
    Äĩ
    -0.75
    wake
    -0.69
    hower
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    uga
    -0.63
    mb
    -0.63
    mand
    -0.62
    hend
    -0.61
    idious
    -0.61
    enary
    -0.61
    POSITIVE LOGITS
     metic
    0.63
     Arcade
    0.63
     lett
    0.62
    Arcade
    0.62
     ASCII
    0.61
     arcade
    0.59
    çİĭ
    0.57
     Disorder
    0.57
     Stun
    0.55
     omega
    0.55
    Activations Density 0.505%

    No Known Activations