© 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 49152
    9. 8-RES_FS49152-JB
    11. 26668
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or acronyms in the context of various activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    314
    +0.12
    0.6%
    373
    +0.11
    0.5%
    412
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.12
    0.02
    314
    +0.11
    0.01
    508
    +0.09
    0.02
    Negative Logits
    doms
    -0.70
    wards
    -0.69
    rooms
    -0.67
    come
    -0.66
    dom
    -0.65
    alties
    -0.65
     dwarves
    -0.60
    fitting
    -0.59
     Bowser
    -0.59
    packs
    -0.59
    POSITIVE LOGITS
    ENN
    1.05
    UFF
    0.99
    AN
    0.98
    VID
    0.96
    INK
    0.95
    ICLE
    0.93
    IK
    0.92
    ARE
    0.91
    ANE
    0.91
    HO
    0.90
    Activations Density 0.050%

    No Known Activations