© 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 1536
    9. 8-RES_FS1536-JB
    11. 67
    Prev
    Next
    INDEX
    Explanations

    celebrity-related terms and names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    447
    +0.13
    0.6%
    554
    +0.13
    0.6%
    686
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.16
    686
    +0.13
    0.07
    554
    +0.13
    -0.00
    Negative Logits
    ascript
    -0.80
    cise
    -0.79
    thia
    -0.74
    ©¶æ
    -0.74
    thur
    -0.67
    shall
    -0.66
    abus
    -0.66
    THER
    -0.65
     digestion
    -0.64
    plete
    -0.62
    POSITIVE LOGITS
    rities
    0.98
    ocl
    0.94
     celebrity
    0.88
     endors
    0.86
     endorsements
    0.81
     performer
    0.80
     celebrities
    0.78
     performers
    0.77
     bearer
    0.76
     tabloid
    0.75
    Activations Density 2.946%

    No Known Activations