© 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. 19614
    Prev
    Next
    INDEX
    Explanations

    mentions of leaves, perceived as a common or unusual element

    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
    289
    +0.12
    0.5%
    21
    +0.10
    0.5%
    361
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.12
    0.01
    289
    +0.10
    0.01
    21
    +0.10
    0.01
    Negative Logits
    PDATE
    -0.86
    ALLY
    -0.66
    ENTION
    -0.64
     adjud
    -0.64
    ICAN
    -0.63
    alty
    -0.63
    anyahu
    -0.63
    cedes
    -0.62
     indemn
    -0.61
    USS
    -0.61
    POSITIVE LOGITS
    let
    1.25
    lets
    1.11
    leaf
    1.04
    leted
    0.96
    iard
    0.92
    worm
    0.92
    ho
    0.92
    overs
    0.91
     leaf
    0.91
    worker
    0.86
    Activations Density 0.021%

    No Known Activations