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. 12021
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or ownership

    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
    393
    +0.11
    0.5%
    409
    +0.11
    0.5%
    611
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.11
    0.02
    611
    +0.11
    0.02
    608
    +0.11
    0.02
    Negative Logits
    anish
    -0.81
    wcs
    -0.71
    hend
    -0.71
    jad
    -0.71
    miah
    -0.68
    ouses
    -0.67
    kward
    -0.66
    ernand
    -0.66
     ][
    -0.64
    wa
    -0.63
    POSITIVE LOGITS
     GDP
    1.02
     blame
    0.84
     responsibility
    0.83
     profits
    0.82
     royalties
    0.79
     revenue
    0.78
     revenues
    0.77
     pie
    0.77
     wealth
    0.71
     income
    0.69
    Activations Density 0.040%

    No Known Activations