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 49152
    5. 8-RES_FS49152-JB
    6. 26258
    Prev
    Next
    INDEX
    Explanations

    references to gaming platforms and digital distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.15
    0.7%
    434
    +0.10
    0.5%
    330
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.15
    0.03
    272
    +0.10
    0.03
    288
    +0.10
    0.04
    Negative Logits
    zsche
    -0.86
    ndra
    -0.82
    rious
    -0.75
    involved
    -0.69
     Job
    -0.69
    alin
    -0.67
    laus
    -0.67
    acci
    -0.65
    orius
    -0.64
    oleon
    -0.63
    POSITIVE LOGITS
     paperback
    1.05
     shelves
    1.04
     theaters
    1.01
     streaming
    0.91
     formats
    0.90
     distributors
    0.88
     ebook
    0.88
     PlayStation
    0.86
     editions
    0.86
     DRM
    0.84
    Activations Density 0.187%

    No Known Activations