© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 24413
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "some."

    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
    447
    +0.35
    1.7%
    480
    +0.24
    1.2%
    87
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.35
    0.04
    85
    +0.24
    0.04
    585
    +0.13
    0.04
    Negative Logits
     Mobil
    -0.70
    Mobil
    -0.68
     Borders
    -0.66
     Nare
    -0.63
    edIn
    -0.62
     Jagu
    -0.62
     Azerb
    -0.62
     Seym
    -0.61
     Gibraltar
    -0.61
     Krug
    -0.60
    POSITIVE LOGITS
     ][
    0.88
     english
    0.70
    voice
    0.68
    fif
    0.63
     )]
    0.62
    coins
    0.62
     );
    0.62
     )))
    0.61
     ]
    0.61
     ))
    0.61
    Activations Density 0.107%

    No Known Activations