© 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. 37239
    Prev
    Next
    INDEX
    Explanations

    content related to significant cultural or entertainment events

    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
    365
    +0.12
    0.5%
    127
    +0.12
    0.5%
    575
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.12
    0.09
    23
    +0.12
    0.08
    575
    +0.11
    0.08
    Negative Logits
     shack
    -0.63
    anwhile
    -0.62
     Glou
    -0.61
    bda
    -0.61
     sidx
    -0.61
     Zup
    -0.60
     scattering
    -0.60
    theless
    -0.59
    ifications
    -0.58
     sled
    -0.58
    POSITIVE LOGITS
    ¬
    1.11
    ı
    1.04
    į
    1.01
    º
    0.99
    Ĵ
    0.99
    ľ
    0.98
    »
    0.96
    Ķ
    0.96
    ´
    0.95
    ¤
    0.94
    Activations Density 0.164%

    No Known Activations