© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 25768
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    314
    +0.17
    0.8%
    639
    +0.12
    0.6%
    640
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.17
    0.05
    314
    +0.12
    0.02
    124
    +0.10
    0.04
    Negative Logits
     Reloaded
    -0.83
     tweaked
    -0.81
     analytics
    -0.80
     revamped
    -0.80
     emoji
    -0.79
     Hughes
    -0.79
     Grimes
    -0.79
     Silicon
    -0.79
     upscale
    -0.78
     upgraded
    -0.78
    POSITIVE LOGITS
    lance
    1.14
    bearing
    1.14
    bour
    1.11
    ships
    1.11
    ship
    1.06
    sit
    1.05
    slave
    1.05
    sac
    1.05
    tri
    1.03
    chance
    1.03
    Activations Density 0.069%

    No Known Activations