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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2306
    Prev
    Next
    INDEX
    Explanations

    phrases signaling the beginning of a new passage or section in text

    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
    276
    +0.11
    0.5%
    186
    +0.10
    0.5%
    136
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.11
    0.06
    276
    +0.10
    0.06
    377
    +0.10
    0.06
    Negative Logits
     Archdemon
    -0.61
    arij
    -0.60
    natureconservancy
    -0.59
     sshd
    -0.58
     Breath
    -0.56
     Strait
    -0.56
    ONSORED
    -0.55
    Edge
    -0.54
    mong
    -0.54
    iven
    -0.53
    POSITIVE LOGITS
    tics
    1.33
    tical
    1.32
    abouts
    1.26
    tic
    1.09
    after
    0.86
     Comes
    0.84
    with
    0.81
    adays
    0.80
    upon
    0.79
    ford
    0.77
    Activations Density 0.259%

    No Known Activations