© 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 24576
    5. 8-RES_FS24576-JB
    6. 1341
    Prev
    Next
    INDEX
    Explanations

    the word "back" with varying intensity across different contexts

    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
    96
    +0.10
    0.5%
    639
    +0.10
    0.5%
    727
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.10
    0.02
    727
    +0.10
    0.02
    50
    +0.10
    0.02
    Negative Logits
     Parenthood
    -0.77
    inational
    -0.71
    risome
    -0.68
    ISION
    -0.67
    cules
    -0.67
    kish
    -0.63
    isions
    -0.61
    cular
    -0.61
    entric
    -0.61
    女
    -0.61
    POSITIVE LOGITS
    wards
    1.21
    lash
    1.21
    doors
    1.03
    door
    1.03
    packing
    1.01
    ward
    1.00
    GROUND
    0.99
    dated
    0.95
    haul
    0.94
    strap
    0.94
    Activations Density 0.034%

    No Known Activations