© 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 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. 43007
    Prev
    Next
    INDEX
    Explanations

    elements related to educational practices and the critique of educational systems

    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
    756
    +0.10
    0.5%
    71
    +0.09
    0.4%
    320
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.06
    546
    +0.09
    0.06
    765
    +0.09
    0.06
    Negative Logits
    orem
    -0.80
    rio
    -0.75
    pheus
    -0.75
    xb
    -0.74
    asma
    -0.73
    ropolis
    -0.72
    oret
    -0.71
    atorium
    -0.70
    xe
    -0.70
    mx
    -0.69
    POSITIVE LOGITS
     respectively
    2.22
     alike
    1.23
    depending
    1.19
     etc
    1.09
     depending
    1.05
     moreover
    1.04
    etc
    1.00
     plus
    0.93
     among
    0.93
     furthermore
    0.92
    Activations Density 0.255%

    No Known Activations