© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9400
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and recipes

    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
    759
    +0.12
    0.6%
    426
    +0.11
    0.5%
    23
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.12
    0.10
    426
    +0.11
    0.09
    23
    +0.11
    0.10
    Negative Logits
     guiActiveUnfocused
    -0.81
     shack
    -0.70
     publicity
    -0.66
     RAD
    -0.66
     assembly
    -0.65
     Palest
    -0.64
     ignition
    -0.63
     scattering
    -0.63
     Zup
    -0.63
     snacks
    -0.63
    POSITIVE LOGITS
    ¤
    1.19
    £
    1.17
    ª
    1.12
    Ĵ
    1.03
    º
    1.02
    Ķ
    1.02
    ¼
    1.01
    ¢
    1.01
    ¬
    1.00
    ĸ
    1.00
    Activations Density 0.152%

    No Known Activations