© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 6673
    Prev
    Next
    INDEX
    Explanations

    verbs related to understanding and concepts in a deeper spiritual or philosophical context

    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
    639
    +0.11
    0.5%
    219
    +0.09
    0.4%
    30
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.11
    0.05
    639
    +0.09
    0.04
    288
    +0.09
    0.05
    Negative Logits
    inately
    -0.84
    igmatic
    -0.80
    eva
    -0.73
    heric
    -0.67
    redo
    -0.66
    ordon
    -0.66
    ieving
    -0.66
    omet
    -0.65
    gettable
    -0.64
    isively
    -0.64
    POSITIVE LOGITS
     spree
    1.09
    tons
    0.98
     ceremony
    0.96
    redients
    0.93
     mechanism
    0.89
     ability
    0.89
     process
    0.87
     ceremonies
    0.82
     frenzy
    0.81
     thereof
    0.79
    Activations Density 0.234%

    No Known Activations