© 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. 10626
    Prev
    Next
    INDEX
    Explanations

    references to specific gaming consoles and platforms

    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
    578
    +0.12
    0.6%
    314
    +0.10
    0.5%
    659
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.12
    0.03
    388
    +0.10
    0.03
    659
    +0.10
    0.03
    Negative Logits
    kson
    -0.80
     Lauder
    -0.72
     TODAY
    -0.69
    kamp
    -0.67
    Ú
    -0.66
    Interstitial
    -0.66
     captcha
    -0.65
     Pru
    -0.64
    sburgh
    -0.63
    getic
    -0.63
    POSITIVE LOGITS
    avier
    1.21
    peria
    1.19
    posed
    1.19
    yz
    1.18
    anth
    1.03
    XXXX
    1.03
    IX
    0.98
    iao
    0.96
    BOX
    0.94
    xxxxxxxx
    0.89
    Activations Density 0.055%

    No Known Activations