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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20052
    Prev
    Next
    INDEX
    Explanations

    the word "blend" and related terms in sentences, such as blending options or blending groups

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    274
    +0.12
    0.6%
    128
    +0.11
    0.5%
    537
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    220
    +0.11
    0.01
    274
    +0.10
    0.01
    Negative Logits
    resy
    -0.74
     reper
    -0.73
    phis
    -0.67
    selves
    -0.66
    irez
    -0.64
     Hanson
    -0.63
    otes
    -0.63
    ktop
    -0.61
    inez
    -0.61
     Dogs
    -0.60
    POSITIVE LOGITS
     blend
    0.85
     seamlessly
    0.83
     blending
    0.82
     Flavoring
    0.80
     blends
    0.75
    endor
    0.74
    rily
    0.73
    wana
    0.72
     together
    0.71
    efully
    0.71
    Activations Density 0.023%

    No Known Activations