© 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 24576
    9. 8-RES_FS24576-JB
    11. 19778
    Prev
    Next
    INDEX
    Explanations

    phrases related to being involved or requiring participation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.11
    0.5%
    236
    +0.10
    0.5%
    624
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.11
    0.03
    562
    +0.10
    0.02
    569
    +0.09
    0.02
    Negative Logits
    toggle
    -0.79
    Enlarge
    -0.75
    soon
    -0.75
    zon
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    geist
    -0.69
    norm
    -0.69
    haar
    -0.69
    oiler
    -0.68
    bell
    -0.68
    POSITIVE LOGITS
     injecting
    0.84
     importing
    0.83
     removing
    0.83
     brute
    0.81
     downloading
    0.80
     swapping
    0.80
     inserting
    0.76
     extracting
    0.76
     sacrificing
    0.74
     coercion
    0.74
    Activations Density 0.051%

    No Known Activations