© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22649
    Prev
    Next
    INDEX
    Explanations

    phrases that convey friendliness or a welcoming tone

    oai_token-act-pair · gpt-4o-miniTriggered 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
    459
    +0.12
    0.5%
    385
    +0.11
    0.5%
    317
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.12
    0.02
    763
    +0.11
    0.01
    730
    +0.10
    0.01
    Negative Logits
    illion
    -0.85
    rast
    -0.84
    ĸļ
    -0.82
    aeda
    -0.75
    ahar
    -0.74
    illon
    -0.74
    ember
    -0.73
    urities
    -0.73
    IGHTS
    -0.72
    umat
    -0.72
    POSITIVE LOGITS
     confines
    0.90
    liness
    0.87
    liest
    0.81
     spirits
    0.81
     friendly
    0.79
     reminder
    0.78
     banter
    0.77
     hello
    0.77
     demeanor
    0.76
     smile
    0.74
    Activations Density 0.037%

    No Known Activations