© 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. 7898
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and building components

    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
    216
    +0.15
    0.7%
    459
    +0.13
    0.6%
    325
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.15
    0.03
    216
    +0.13
    0.02
    42
    +0.12
    0.02
    Negative Logits
    izon
    -0.88
    mia
    -0.77
    ican
    -0.76
    ricular
    -0.74
    phant
    -0.74
    andra
    -0.72
    bered
    -0.68
    utical
    -0.67
    my
    -0.66
     Lauder
    -0.66
    POSITIVE LOGITS
    smanship
    0.85
    builder
    0.78
     builder
    0.75
     kits
    0.73
    mud
    0.73
    bot
    0.72
    building
    0.71
    packs
    0.70
    raft
    0.70
    bots
    0.70
    Activations Density 0.032%

    No Known Activations