© 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. 10410
    Prev
    Next
    INDEX
    Explanations

    terms related to conspiracy theories and controversial topics

    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
    195
    +0.10
    0.5%
    187
    +0.10
    0.4%
    385
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.10
    0.02
    365
    +0.10
    0.01
    522
    +0.09
    0.02
    Negative Logits
     Ancients
    -0.79
     Everywhere
    -0.76
     Manip
    -0.68
     Gravity
    -0.67
     Boko
    -0.66
    BuyableInstoreAndOnline
    -0.64
    ONES
    -0.62
     gag
    -0.62
     Authority
    -0.61
     Mori
    -0.61
    POSITIVE LOGITS
    eport
    1.22
    eway
    1.21
    emen
    1.18
    estone
    1.14
    estyle
    1.11
    eland
    1.11
    eman
    1.09
    eware
    1.03
    ck
    1.03
    ighter
    1.03
    Activations Density 0.050%

    No Known Activations