© 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. 1233
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical concepts or scientific explanations

    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
    512
    +0.10
    0.5%
    217
    +0.10
    0.4%
    317
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.04
    512
    +0.10
    0.03
    272
    +0.10
    0.03
    Negative Logits
    plets
    -0.71
    idav
    -0.70
    chel
    -0.64
    Shut
    -0.61
    MAP
    -0.61
    skirts
    -0.61
    Downloadha
    -0.60
    pes
    -0.60
    etsk
    -0.59
     Walls
    -0.58
    POSITIVE LOGITS
     magnitude
    1.14
     stature
    1.06
     caliber
    1.05
     calib
    1.01
     utmost
    1.00
     importance
    0.92
     il
    0.91
     sorts
    0.91
     nature
    0.91
     renown
    0.91
    Activations Density 0.388%

    No Known Activations