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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24292
    Prev
    Next
    INDEX
    Explanations

    monetary values or financial figures

    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
    620
    +0.10
    0.5%
    63
    +0.09
    0.4%
    157
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.02
    230
    +0.09
    0.02
    383
    +0.09
    0.02
    Negative Logits
    interstitial
    -0.76
    abilities
    -0.75
    quez
    -0.70
    anthrop
    -0.69
    hip
    -0.68
     strugg
    -0.68
    fruit
    -0.66
    alities
    -0.65
     bottled
    -0.64
    ographically
    -0.63
    POSITIVE LOGITS
    mAh
    0.83
    ISTER
    0.82
    rpm
    0.79
    gp
    0.75
    Hz
    0.75
    âĤ¬
    0.72
    ertain
    0.72
     GHz
    0.70
    /#
    0.70
    MHz
    0.69
    Activations Density 0.025%

    No Known Activations