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. 23503
    Prev
    Next
    INDEX
    Explanations

    actions or conditions related to being in a state of restriction or limitation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    241
    +0.11
    0.5%
    454
    +0.10
    0.5%
    665
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.07
    70
    +0.10
    0.05
    469
    +0.10
    0.04
    Negative Logits
     Forge
    -0.63
     convergence
    -0.63
     infrared
    -0.61
     UE
    -0.60
     genesis
    -0.60
     Stability
    -0.59
     Alps
    -0.59
     OpenGL
    -0.58
     Torrent
    -0.58
     AU
    -0.58
    POSITIVE LOGITS
     aback
    1.07
     hostage
    0.96
    otyp
    0.93
     captive
    0.90
    uled
    0.86
    opted
    0.86
    quished
    0.86
    ardless
    0.85
    washed
    0.85
    ifferent
    0.82
    Activations Density 0.230%

    No Known Activations