© 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. 1258
    Prev
    Next
    INDEX
    Explanations

    words related to technology and specific user groups

    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
    481
    +0.20
    0.9%
    447
    +0.17
    0.8%
    330
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.20
    0.07
    32
    +0.17
    0.07
    224
    +0.11
    0.06
    Negative Logits
    Hig
    -0.74
    Thumbnail
    -0.70
    ãĤ¦ãĤ¹
    -0.69
    ASED
    -0.68
    TEXTURE
    -0.64
    INGS
    -0.63
    SET
    -0.60
    âĶĢâĶĢâĶĢâĶĢ
    -0.60
    strument
    -0.60
    SPONSORED
    -0.60
    POSITIVE LOGITS
     beware
    1.29
    hip
    1.16
     rejoice
    1.14
    paces
    1.06
    chool
    1.05
     everywhere
    1.03
    peak
    1.03
    hips
    1.02
    aurus
    0.98
    wana
    0.98
    Activations Density 0.298%

    No Known Activations