© 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. 20217
    Prev
    Next
    INDEX
    Explanations

    phrases related to unexpected results or revelations

    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
    273
    +0.12
    0.5%
    6
    +0.10
    0.4%
    274
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.12
    0.03
    691
    +0.10
    0.02
    490
    +0.09
    0.02
    Negative Logits
    ngth
    -0.81
    abase
    -0.80
     raft
    -0.75
    ailability
    -0.74
     exting
    -0.72
    ©¶æ
    -0.72
    sembly
    -0.72
    xe
    -0.70
    alach
    -0.70
    rongh
    -0.67
    POSITIVE LOGITS
    DragonMagazine
    0.73
    imaru
    0.69
     anymore
    0.68
    ा
    0.68
     systemd
    0.68
     considering
    0.64
     Pav
    0.63
    EC
    0.62
    UFC
    0.61
    Notice
    0.60
    Activations Density 0.038%

    No Known Activations