© 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 24576
    9. 8-RES_FS24576-JB
    11. 6678
    Prev
    Next
    INDEX
    Explanations

    phrases related to political establishments and power elites

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.17
    0.8%
    481
    +0.13
    0.6%
    401
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.17
    0.06
    288
    +0.13
    0.06
    509
    +0.12
    0.04
    Negative Logits
    ishable
    -0.70
     Plate
    -0.69
     Theft
    -0.65
    catch
    -0.62
     pedestrian
    -0.61
    Ô
    -0.60
     Width
    -0.58
    col
    -0.58
    paren
    -0.56
     Tess
    -0.56
    POSITIVE LOGITS
    members
    0.94
     assembled
    0.88
    leaders
    0.88
     alike
    0.88
    erity
    0.88
     members
    0.86
    ariat
    0.82
     hierarchy
    0.80
    ervatives
    0.80
     dysfunction
    0.79
    Activations Density 0.216%

    No Known Activations