© 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. 26743
    Prev
    Next
    INDEX
    Explanations

    references to user-generated content and sponsorship in a technological context

    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
    0.5%
    115
    +0.10
    0.4%
    354
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.01
    124
    +0.10
    0.03
    610
    +0.10
    0.02
    Negative Logits
    ioxide
    -0.72
    ulhu
    -0.72
     Ply
    -0.70
     Bust
    -0.65
     Pell
    -0.64
     cloves
    -0.64
     bells
    -0.62
    ŃĶ
    -0.62
    arus
    -0.59
     marrow
    -0.59
    POSITIVE LOGITS
    generated
    0.93
    friendly
    0.90
    controlled
    0.87
    defined
    0.84
    centric
    0.83
    facing
    0.81
    activated
    0.79
    centered
    0.78
    \\\\\\\\
    0.75
    created
    0.75
    Activations Density 0.044%

    No Known Activations