© 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 24576
    9. 8-RES_FS24576-JB
    11. 7788
    Prev
    Next
    INDEX
    Explanations

    words related to human ancestors and prehistoric lifestyles

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    477
    +0.12
    0.6%
    46
    +0.12
    0.5%
    711
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.12
    0.05
    477
    +0.12
    0.04
    120
    +0.10
    0.04
    Negative Logits
    ++++
    -0.81
    cia
    -0.75
    ioxide
    -0.69
    rait
    -0.67
    ysis
    -0.66
     ours
    -0.66
    ulhu
    -0.66
     theirs
    -0.64
    milo
    -0.64
    VL
    -0.64
    POSITIVE LOGITS
    gat
    0.84
    Forest
    0.68
    Eight
    0.68
    learn
    0.66
    bart
    0.66
    auld
    0.64
    tale
    0.64
    Howard
    0.64
    poke
    0.63
    bender
    0.62
    Activations Density 0.133%

    No Known Activations