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 24576
    5. 8-RES_FS24576-JB
    6. 21647
    Prev
    Next
    INDEX
    Explanations

    words related to music albums and band influence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    480
    +0.32
    1.6%
    712
    +0.08
    0.4%
    641
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.32
    0.04
    724
    +0.08
    0.06
    480
    +0.08
    -0.01
    Negative Logits
     ðŁĺ
    -0.63
     Repeat
    -0.61
    ãĤĵ
    -0.59
     Twice
    -0.56
    emate
    -0.56
    ainer
    -0.56
     Reload
    -0.55
    #$
    -0.55
     congr
    -0.55
     typo
    -0.54
    POSITIVE LOGITS
     fostering
    0.83
     emphasizing
    0.82
     envision
    0.82
     integrating
    0.80
     embodied
    0.80
     culminating
    0.80
     embracing
    0.76
     envisioned
    0.76
     pioneered
    0.76
     themes
    0.74
    Activations Density 0.833%

    No Known Activations