© 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. 23964
    Prev
    Next
    INDEX
    Explanations

    the word "ra" in various contexts

    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
    269
    +0.13
    0.6%
    739
    +0.12
    0.5%
    520
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.02
    520
    +0.12
    0.02
    343
    +0.10
    0.02
    Negative Logits
    iaries
    -0.74
    icians
    -0.66
     curfew
    -0.65
    regor
    -0.64
    agascar
    -0.63
     Revel
    -0.62
    orem
    -0.62
    ician
    -0.62
     unpop
    -0.61
    aminer
    -0.60
    POSITIVE LOGITS
    irie
    1.26
    fter
    1.24
    fters
    1.23
    eus
    1.21
    ven
    1.15
    ffe
    1.12
    ppa
    1.12
    zzo
    1.12
    ving
    1.11
    plets
    1.10
    Activations Density 0.025%

    No Known Activations