© 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. 1419
    Prev
    Next
    INDEX
    Explanations

    verbs related to positioning or adjusting something in a particular way

    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
    101
    +0.14
    0.6%
    679
    +0.13
    0.6%
    62
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.14
    0.02
    702
    +0.13
    0.01
    62
    +0.10
    0.01
    Negative Logits
    loo
    -0.89
    ilk
    -0.85
    perty
    -0.72
    hell
    -0.72
    bara
    -0.71
    gery
    -0.69
    HAEL
    -0.68
    geoning
    -0.67
    sein
    -0.66
    scene
    -0.65
    POSITIVE LOGITS
    ments
    1.21
    eering
    0.95
    arity
    0.91
     aligned
    0.87
     align
    0.85
     alignment
    0.85
    iances
    0.84
    aligned
    0.81
    icut
    0.79
    inates
    0.78
    Activations Density 0.032%

    No Known Activations