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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 141
    Prev
    Next
    INDEX
    Explanations

    content related to news, events, and community engagement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    526
    +0.12
    0.5%
    269
    +0.12
    0.5%
    568
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.12
    0.08
    568
    +0.12
    0.07
    684
    +0.10
    0.07
    Negative Logits
    uum
    -0.66
    UE
    -0.65
    illary
    -0.62
    osphere
    -0.62
    arium
    -0.61
    KE
    -0.59
    ORY
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.58
    ********************************
    -0.58
    Alpha
    -0.57
    POSITIVE LOGITS
    hang
    1.22
    tones
    1.13
    drive
    1.13
    priced
    1.08
    lord
    1.07
    loading
    1.06
    comes
    1.04
    reaching
    1.03
    grown
    1.03
    whelming
    1.02
    Activations Density 2.099%

    No Known Activations