© 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 49152
    9. 8-RES_FS49152-JB
    11. 45837
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly those related to measurements or prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    98
    +0.10
    0.5%
    583
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.10
    0.03
    230
    +0.10
    0.03
    98
    +0.10
    0.03
    Negative Logits
    arial
    -0.66
    warts
    -0.64
    verend
    -0.63
    soType
    -0.63
    bread
    -0.63
    ancing
    -0.62
    ality
    -0.61
    agan
    -0.60
    ign
    -0.60
    alone
    -0.59
    POSITIVE LOGITS
     MHz
    1.00
    MHz
    0.95
    Hz
    0.90
    +
    0.87
     meters
    0.83
    px
    0.82
    +,
    0.82
     Mile
    0.80
    +.
    0.80
     metres
    0.80
    Activations Density 0.035%

    No Known Activations