Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8885
    Prev
    Next
    INDEX
    Explanations

    titles or roles of academic and professional positions

    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
    145
    +0.12
    0.5%
    0
    +0.11
    0.5%
    136
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.12
    0.01
    0
    +0.11
    0.01
    136
    +0.10
    0.01
    Negative Logits
    CRIP
    -0.89
    stakes
    -0.85
    abiding
    -0.82
    apo
    -0.81
    enegger
    -0.79
    worms
    -0.78
    panic
    -0.77
    wagen
    -0.77
    cale
    -0.76
    iders
    -0.76
    POSITIVE LOGITS
     dean
    1.13
     professor
    1.04
     newsp
    0.88
     editor
    0.79
     vice
    0.78
     curator
    0.76
     professors
    0.76
     Dean
    0.75
    lly
    0.74
     pastor
    0.71
    Activations Density 0.013%

    No Known Activations