© 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 49152
    9. 8-RES_FS49152-JB
    11. 37365
    Prev
    Next
    INDEX
    Explanations

    references to subscriptions or sign-up actions related to newsletters or emails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    407
    +0.11
    0.5%
    544
    +0.10
    0.5%
    190
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    631
    +0.11
    0.01
    13
    +0.10
    0.01
    111
    +0.10
    0.01
    Negative Logits
    ilts
    -0.81
    erness
    -0.75
    areth
    -0.67
    nesses
    -0.64
    ossus
    -0.63
    uthor
    -0.63
    ahime
    -0.62
     Tracks
    -0.62
    anges
    -0.62
    eters
    -0.62
    POSITIVE LOGITS
     inbox
    0.78
     totaling
    0.78
     roundup
    0.71
     dialog
    0.70
     ðŁ
    0.69
     trending
    0.69
     playlist
    0.65
     selfie
    0.63
    secut
    0.62
     pdf
    0.62
    Activations Density 0.007%

    No Known Activations