© 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. 21058
    Prev
    Next
    INDEX
    Explanations

    financial figures such as monetary values and amounts of money

    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
    495
    +0.10
    0.5%
    185
    +0.10
    0.5%
    545
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.10
    0.03
    352
    +0.10
    0.03
    545
    +0.09
    0.03
    Negative Logits
     zoning
    -0.59
     scrutiny
    -0.57
    Newsletter
    -0.55
     scheduling
    -0.55
     schedules
    -0.54
     deadlines
    -0.53
     equality
    -0.52
     leveling
    -0.52
    Ball
    -0.52
    olerance
    -0.51
    POSITIVE LOGITS
    ),"
    1.06
    )]
    1.02
    )."
    1.00
    ])
    0.94
    )=
    0.92
    )",
    0.92
    )
    0.92
    )"
    0.91
    -)
    0.90
    )--
    0.87
    Activations Density 0.062%

    No Known Activations