© 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. 10829
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential risks or problems

    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
    151
    +0.15
    0.7%
    101
    +0.13
    0.6%
    651
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.15
    0.04
    465
    +0.13
    0.03
    101
    +0.12
    0.03
    Negative Logits
    bern
    -0.92
    baugh
    -0.91
    ablishment
    -0.81
    shi
    -0.78
    ger
    -0.76
    raint
    -0.75
    lins
    -0.74
    iom
    -0.74
    ĸļ
    -0.71
    shire
    -0.70
    POSITIVE LOGITS
     jeopard
    0.99
     contam
    0.86
     incrim
    0.81
     hazardous
    0.81
     combust
    0.77
     lethal
    0.77
     harmful
    0.77
     damaging
    0.76
     contamin
    0.76
     compromising
    0.76
    Activations Density 0.099%

    No Known Activations