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. 26101
    Prev
    Next
    INDEX
    Explanations

    terms related to sea levels and their fluctuations

    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
    19
    +0.13
    0.6%
    420
    +0.10
    0.5%
    152
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.13
    0.02
    607
    +0.10
    0.02
    76
    +0.10
    0.02
    Negative Logits
    ividual
    -0.82
    Interstitial
    -0.82
    sbm
    -0.77
    iaries
    -0.77
    arantine
    -0.76
    ilyn
    -0.76
    etts
    -0.75
    âĶģ
    -0.74
    STEP
    -0.73
    ÑĮ
    -0.73
    POSITIVE LOGITS
    plane
    1.21
    planes
    1.03
     lions
    0.94
    front
    0.92
     lion
    0.90
     breeze
    0.88
     shore
    0.84
     Kraken
    0.83
     serpent
    0.83
     kay
    0.82
    Activations Density 0.011%

    No Known Activations