© 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. 9513
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and discussions

    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
    423
    +0.10
    0.5%
    373
    +0.10
    0.5%
    54
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.10
    0.05
    151
    +0.10
    0.06
    99
    +0.10
    0.04
    Negative Logits
    ousel
    -0.70
    eers
    -0.69
    addock
    -0.68
    ËĪ
    -0.66
    imm
    -0.65
    dies
    -0.65
    aily
    -0.65
    pie
    -0.64
    kamp
    -0.63
    umbn
    -0.61
    POSITIVE LOGITS
    entimes
    1.04
     speaking
    0.95
     importantly
    0.91
     Speaking
    0.90
    withstanding
    0.86
     unsurprisingly
    0.83
    nown
    0.82
    etheless
    0.81
     sensing
    0.77
    ortunately
    0.76
    Activations Density 0.269%

    No Known Activations