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. 23972
    Prev
    Next
    INDEX
    Explanations

    phrases related to governance and administrative oversight

    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
    362
    +0.15
    0.7%
    554
    +0.13
    0.6%
    636
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.10
    608
    +0.13
    0.07
    385
    +0.12
    0.07
    Negative Logits
     nods
    -0.87
    verb
    -0.81
    00200000
    -0.79
    opsis
    -0.77
    iev
    -0.76
    Notes
    -0.76
    hus
    -0.75
    eat
    -0.73
    govtrack
    -0.71
    使
    -0.71
    POSITIVE LOGITS
     workforce
    1.11
     embattled
    1.08
     nation
    0.98
     troubled
    0.98
     workplace
    0.94
     sprawling
    0.91
     lucrative
    0.88
     nascent
    0.88
     Affordable
    0.87
     fledgling
    0.86
    Activations Density 0.338%

    No Known Activations