© 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 24576
    9. 8-RES_FS24576-JB
    11. 18595
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    87
    +0.21
    1.1%
    659
    +0.11
    0.6%
    373
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.21
    0.12
    232
    +0.11
    0.08
    145
    +0.11
    0.07
    Negative Logits
    tumblr
    -0.71
     manipulating
    -0.60
     legacy
    -0.58
     tumble
    -0.58
     supposedly
    -0.57
     partying
    -0.57
     evolved
    -0.57
     unite
    -0.57
     inheritance
    -0.56
     originated
    -0.55
    POSITIVE LOGITS
    anton
    0.81
    ijn
    0.76
    jit
    0.74
    lee
    0.74
    aji
    0.73
     Cohen
    0.73
    elman
    0.73
     Shapiro
    0.73
    elli
    0.72
    arie
    0.72
    Activations Density 0.424%

    No Known Activations