© 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. 10767
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to technical processes involving computers

    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
    675
    +0.11
    0.5%
    172
    +0.11
    0.5%
    29
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.11
    0.05
    29
    +0.11
    0.05
    202
    +0.10
    0.04
    Negative Logits
    TB
    -0.69
    SPONSORED
    -0.68
    Silver
    -0.64
    Nevertheless
    -0.64
    oler
    -0.62
    inea
    -0.62
     Coverage
    -0.62
    atem
    -0.61
    ati
    -0.61
    BSD
    -0.61
    POSITIVE LOGITS
     virtue
    1.25
     default
    1.06
     mistake
    1.02
    products
    1.00
    laws
    0.99
     clicking
    0.95
    akuya
    0.93
    catch
    0.93
    gone
    0.93
     accident
    0.87
    Activations Density 0.103%

    No Known Activations