© 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 24576
    9. 8-RES_FS24576-JB
    11. 19477
    Prev
    Next
    INDEX
    Explanations

    technical information related to camera settings, bidding options in a campaign, and financial figures

    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
    506
    +0.13
    0.6%
    101
    +0.10
    0.5%
    181
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.13
    0.04
    506
    +0.10
    0.03
    289
    +0.10
    0.01
    Negative Logits
     gon
    -0.77
     Nep
    -0.75
     vi
    -0.74
     Jos
    -0.74
     ris
    -0.73
    ni
    -0.73
     adj
    -0.73
     Jays
    -0.73
     Kaplan
    -0.71
     Lamar
    -0.70
    POSITIVE LOGITS
    50
    1.13
    100
    1.11
    150
    1.09
    200
    1.09
    1000
    1.08
    60
    1.06
    80
    1.05
    300
    1.02
    700
    1.00
    400
    1.00
    Activations Density 0.171%

    No Known Activations