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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 375
    Prev
    Next
    INDEX
    Explanations

    verbs related to providing service or serving in a positive manner

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    314
    +0.10
    0.5%
    761
    +0.09
    0.4%
    62
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.10
    0.05
    61
    +0.09
    0.04
    59
    +0.09
    0.03
    Negative Logits
    vu
    -0.68
    razil
    -0.67
     Chase
    -0.64
     converter
    -0.64
    pex
    -0.63
    ascus
    -0.62
     skating
    -0.60
    opher
    -0.60
    iser
    -0.58
    iques
    -0.57
    POSITIVE LOGITS
    HTTP
    0.82
     horm
    0.75
    entials
    0.73
    VERTISEMENT
    0.72
    fully
    0.71
     meals
    0.71
    maid
    0.71
    ences
    0.71
    lyak
    0.71
    iments
    0.70
    Activations Density 0.493%

    No Known Activations