© 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. 19660
    Prev
    Next
    INDEX
    Explanations

    people involved in significant events or controversial actions

    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
    447
    +0.11
    0.5%
    193
    +0.10
    0.5%
    139
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.11
    0.04
    551
    +0.10
    0.04
    149
    +0.10
    0.03
    Negative Logits
    ply
    -0.76
    inters
    -0.69
    ivable
    -0.67
    strip
    -0.66
     drying
    -0.66
    detail
    -0.65
    course
    -0.64
    usage
    -0.63
     guiActiveUnfocused
    -0.62
    Ble
    -0.61
    POSITIVE LOGITS
     oversaw
    1.05
     oversees
    0.88
     governs
    0.85
     preceded
    0.82
     presided
    0.81
     accompanies
    0.78
     owns
    0.77
     pioneered
    0.77
     spawned
    0.76
     superv
    0.76
    Activations Density 0.118%

    No Known Activations