© 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. 41495
    Prev
    Next
    INDEX
    Explanations

    references to escalating tensions or issues

    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
    640
    +0.10
    0.5%
    3
    +0.10
    0.4%
    608
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.10
    0.03
    725
    +0.10
    0.03
    684
    +0.09
    0.02
    Negative Logits
    uum
    -1.02
    ãĥ¼ãĥĨãĤ£
    -0.90
    OH
    -0.77
    oooooooo
    -0.75
    Vi
    -0.73
    ï¸
    -0.71
    igmatic
    -0.71
    GH
    -0.71
    OGR
    -0.71
    DEV
    -0.71
    POSITIVE LOGITS
    tones
    1.11
    reaching
    0.89
    lord
    0.85
    reach
    0.85
     whether
    0.85
    loading
    0.83
    comes
    0.83
    priced
    0.83
    haul
    0.82
     matters
    0.81
    Activations Density 0.036%

    No Known Activations