© 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. 25759
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and 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_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
    480
    +0.32
    1.5%
    447
    +0.16
    0.8%
    464
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.32
    0.04
    165
    +0.16
    0.03
    495
    +0.14
    0.04
    Negative Logits
    unci
    -0.68
     citiz
    -0.65
    onga
    -0.62
     Vaugh
    -0.62
     princ
    -0.61
    ework
    -0.59
    akespe
    -0.58
    ãĤ©
    -0.58
    querque
    -0.57
     proble
    -0.56
    POSITIVE LOGITS
    -$
    0.97
    /$
    0.91
    USD
    0.91
     Billion
    0.89
     USD
    0.83
    billion
    0.82
    /+
    0.81
     MILL
    0.80
     billion
    0.80
    million
    0.78
    Activations Density 0.058%

    No Known Activations