© 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. 41800
    Prev
    Next
    INDEX
    Explanations

    phrases related to freeing up space or resources

    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
    388
    +0.11
    0.5%
    642
    +0.09
    0.4%
    236
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.11
    0.01
    761
    +0.09
    0.01
    658
    +0.09
    0.01
    Negative Logits
    gins
    -0.68
     mathemat
    -0.64
    BuyableInstoreAndOnline
    -0.63
     Wiz
    -0.62
     Fidel
    -0.62
     Sins
    -0.61
    Lab
    -0.61
    come
    -0.60
    mania
    -0.59
    FO
    -0.59
    POSITIVE LOGITS
     space
    1.07
     resources
    0.98
     spots
    0.92
     valuable
    0.88
     acres
    0.85
     spaces
    0.85
     slots
    0.83
    itures
    0.80
     considerable
    0.78
     precious
    0.77
    Activations Density 0.023%

    No Known Activations