© 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. 22226
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, particularly places referred to as "land."

    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
    288
    +0.13
    0.6%
    414
    +0.12
    0.6%
    624
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.13
    0.02
    4
    +0.12
    0.02
    414
    +0.12
    0.01
    Negative Logits
     cumbers
    -0.78
    chel
    -0.71
    ongyang
    -0.70
    displayText
    -0.70
     retribution
    -0.68
     inaction
    -0.67
    hift
    -0.66
     millenn
    -0.66
     undermin
    -0.65
    externalActionCode
    -0.64
    POSITIVE LOGITS
    scape
    1.06
    marks
    0.94
     Islands
    0.90
     Park
    0.89
     Hills
    0.87
    estine
    0.85
    ishly
    0.83
     County
    0.83
     Heights
    0.82
    town
    0.79
    Activations Density 0.032%

    No Known Activations