© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12571
    Prev
    Next
    INDEX
    Explanations

    phrases related to a particular venue or location, specifically the name "Arena" followed by a number

    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
    288
    +0.16
    0.7%
    86
    +0.11
    0.5%
    46
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.02
    693
    +0.11
    0.02
    11
    +0.10
    0.01
    Negative Logits
    reads
    -0.95
    nir
    -0.85
    yon
    -0.73
    dit
    -0.73
    lessly
    -0.71
    orders
    -0.69
    lust
    -0.68
    redo
    -0.67
    ILY
    -0.67
    teenth
    -0.67
    POSITIVE LOGITS
     arena
    0.96
     arenas
    0.93
    nas
    0.84
    adium
    0.82
    Aren
    0.77
     stadiums
    0.77
     seating
    0.76
     announcer
    0.76
    Net
    0.74
     venue
    0.73
    Activations Density 0.029%

    No Known Activations