© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7562
    Prev
    Next
    INDEX
    Explanations

    words related to ideologies or belief systems

    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
    216
    +0.11
    0.5%
    267
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.11
    0.03
    247
    +0.11
    0.02
    510
    +0.11
    0.02
    Negative Logits
    FACE
    -0.80
    ãģ®éŃĶ
    -0.77
    shown
    -0.73
    STON
    -0.70
    é¾
    -0.68
    MENTS
    -0.68
    zens
    -0.64
    ths
    -0.64
    ĸļ
    -0.63
    ãĥ¼ãĥ«
    -0.61
    POSITIVE LOGITS
    ische
    0.91
     tendencies
    0.86
     extraord
    0.82
    ischer
    0.82
    otle
    0.81
    ophical
    0.78
    ribution
    0.78
     manifesto
    0.76
    ricting
    0.75
    emi
    0.74
    Activations Density 0.050%

    No Known Activations