© 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. 12282
    Prev
    Next
    INDEX
    Explanations

    the word "by" preceding a number, indicating attribution or agency

    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
    616
    +0.12
    0.5%
    289
    +0.10
    0.5%
    22
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.12
    0.05
    29
    +0.10
    0.05
    22
    +0.09
    0.04
    Negative Logits
    istan
    -0.58
     digs
    -0.57
    ptions
    -0.57
    ounter
    -0.56
     retard
    -0.56
    regon
    -0.56
    earable
    -0.55
    itives
    -0.55
    hess
    -0.53
    imal
    -0.53
    POSITIVE LOGITS
    products
    1.32
     virtue
    1.27
    product
    1.08
    laws
    1.07
    akuya
    1.06
     implication
    1.02
    gone
    1.01
     default
    0.99
    catch
    0.96
     extension
    0.93
    Activations Density 0.123%

    No Known Activations