© 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. 9850
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific historical events

    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
    728
    +0.10
    0.4%
    93
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.10
    0.04
    344
    +0.09
    0.04
    93
    +0.09
    0.03
    Negative Logits
    opers
    -0.91
    emies
    -0.83
    emy
    -0.82
    ħĭ
    -0.76
    ivas
    -0.75
    etts
    -0.74
    ffield
    -0.73
    pherd
    -0.72
    ologies
    -0.70
    ooters
    -0.69
    POSITIVE LOGITS
     ado
    0.91
     emphasis
    0.89
     misinformation
    0.81
     confusion
    0.81
     speculation
    0.80
     resemblance
    0.76
     similarity
    0.75
     hinges
    0.74
     else
    0.72
    body
    0.72
    Activations Density 0.100%

    No Known Activations