© 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. 1681
    Prev
    Next
    INDEX
    Explanations

    information related to spy software and mobile phone tracking

    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
    451
    +0.14
    0.6%
    756
    +0.11
    0.5%
    674
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.14
    0.06
    255
    +0.11
    0.06
    679
    +0.11
    0.11
    Negative Logits
     Slate
    -1.00
     Ramsay
    -0.88
     BuzzFeed
    -0.85
     ÂŃ
    -0.83
    )—
    -0.82
     Baker
    -0.82
     Watkins
    -0.81
    —
    -0.81
     Walker
    -0.81
    —"
    -0.80
    POSITIVE LOGITS
    ´
    1.11
     dont
    1.01
     happ
    0.99
     secondly
    0.99
    iour
    0.99
     resear
    0.98
    pecially
    0.98
     analyse
    0.97
     till
    0.96
     doesnt
    0.96
    Activations Density 2.873%

    No Known Activations