© 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. 6563
    Prev
    Next
    INDEX
    Explanations

    common terms related to technology and government surveillance

    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
    218
    +0.27
    1.6%
    373
    +0.22
    1.3%
    497
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.27
    -0.03
    218
    +0.22
    0.03
    284
    +0.11
    0.04
    Negative Logits
    plan
    -0.66
    jug
    -0.59
    bye
    -0.54
    qv
    -0.53
    comb
    -0.50
     directions
    -0.49
    atto
    -0.48
    dial
    -0.47
     symmetry
    -0.46
     vigorously
    -0.46
    POSITIVE LOGITS
    ENTS
    0.60
    ENT
    0.52
    ardless
    0.52
    ENCE
    0.51
    ENCY
    0.51
    åŃIJ
    0.50
    athed
    0.48
    ĩ
    0.48
    aunts
    0.48
    ents
    0.48
    Activations Density 0.294%

    No Known Activations