© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23934
    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
    373
    +0.11
    0.5%
    84
    +0.11
    0.5%
    241
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    205
    +0.11
    0.01
    578
    +0.11
    0.01
    120
    +0.10
    0.01
    Negative Logits
     seeker
    -0.68
    baugh
    -0.66
     Blaz
    -0.66
    storm
    -0.61
     Silk
    -0.61
     Pom
    -0.60
     Bram
    -0.60
     Spit
    -0.60
     Piet
    -0.59
     Poo
    -0.58
    POSITIVE LOGITS
    interstitial
    0.97
    1000
    0.78
    uild
    0.77
    ģ«
    0.76
    /-
    0.76
    100
    0.74
    150
    0.72
    £
    0.72
    untu
    0.71
    /$
    0.71
    Activations Density 0.015%

    No Known Activations