© 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 49152
    5. 8-RES_FS49152-JB
    6. 45771
    Prev
    Next
    INDEX
    Explanations

    references to tools and utilities

    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
    420
    +0.14
    0.6%
    679
    +0.13
    0.6%
    289
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.14
    0.02
    653
    +0.13
    0.02
    50
    +0.11
    0.02
    Negative Logits
     Sons
    -0.86
    ãģ®å®
    -0.66
     sons
    -0.65
     Qiao
    -0.63
     adolesc
    -0.63
     decad
    -0.61
     millenn
    -0.60
     iod
    -0.60
     mosqu
    -0.60
     Reincarn
    -0.58
    POSITIVE LOGITS
    tips
    1.58
    kit
    1.56
    tip
    1.29
    sonian
    1.18
    belt
    1.12
    box
    1.10
    chain
    1.09
    set
    1.08
    chains
    1.02
    boxes
    1.01
    Activations Density 0.013%

    No Known Activations