© 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. 23986
    Prev
    Next
    INDEX
    Explanations

    visual features and elements related to design or imagery

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.20
    0.9%
    578
    +0.13
    0.6%
    497
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.20
    0.06
    326
    +0.13
    0.05
    27
    +0.12
    0.05
    Negative Logits
    Delivery
    -0.82
    Honest
    -0.74
    PDATE
    -0.71
    =-=-=-=-=-=-=-=-
    -0.69
     Competitive
    -0.68
    ACTED
    -0.68
    gets
    -0.67
    CLASS
    -0.67
    racuse
    -0.65
    Winner
    -0.63
    POSITIVE LOGITS
     protr
    1.22
    pots
    1.18
    mith
    1.10
    hips
    1.10
    poons
    1.08
    paces
    1.07
    heet
    1.07
    pring
    1.05
    pace
    1.04
    cape
    0.99
    Activations Density 0.246%

    No Known Activations