© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45486
    Prev
    Next
    INDEX
    Explanations

    references to time or dates in the context of planning or scheduling

    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
    373
    +0.11
    0.5%
    185
    +0.10
    0.5%
    311
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.11
    0.01
    394
    +0.10
    0.01
    311
    +0.09
    0.00
    Negative Logits
    DO
    -0.70
    Bet
    -0.67
    bush
    -0.66
    theless
    -0.64
    hops
    -0.61
    answer
    -0.59
     Antar
    -0.59
     assum
    -0.58
    HAHA
    -0.57
    going
    -0.57
    POSITIVE LOGITS
     Sketch
    1.61
    ãĥĨãĤ£
    0.81
    ï¸
    0.76
    ãĥ´ãĤ¡
    0.75
     Created
    0.74
    qqa
    0.72
    roud
    0.71
    azon
    0.70
    ãĥķãĤ©
    0.70
    notations
    0.69
    Activations Density 0.003%

    No Known Activations