© 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 12288
    9. 8-RES_FS12288-JB
    11. 9377
    Prev
    Next
    INDEX
    Explanations

    time and scheduling related information marked by days, dates, and times

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    114
    +0.13
    0.6%
    640
    +0.12
    0.6%
    6
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.13
    0.06
    6
    +0.12
    0.05
    336
    +0.11
    0.04
    Negative Logits
     answ
    -0.72
     artif
    -0.71
    tering
    -0.70
    Ļ½
    -0.68
     compan
    -0.67
    omore
    -0.66
    ãĥ¥
    -0.65
     footing
    -0.65
    rew
    -0.64
    itory
    -0.64
    POSITIVE LOGITS
     âĵĺ
    0.87
     Committees
    0.82
     Frames
    0.78
     =>
    0.74
     Races
    0.72
    âķ
    0.72
     :
    0.70
     Alternatively
    0.70
    ↵↵
    0.70
     =================================================================
    0.70
    Activations Density 0.153%

    No Known Activations