© 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 49152
    9. 8-RES_FS49152-JB
    11. 42926
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, particularly places related to Czechia and its geographical aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    588
    +0.10
    0.5%
    48
    +0.10
    0.5%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.10
    0.01
    4
    +0.10
    0.01
    588
    +0.10
    0.01
    Negative Logits
    Accessory
    -0.79
    IBLE
    -0.72
    aminer
    -0.72
     rapt
    -0.67
    Hum
    -0.64
     avoidance
    -0.64
     watering
    -0.64
     mist
    -0.64
    Hug
    -0.63
     breaker
    -0.62
    POSITIVE LOGITS
    akia
    1.27
    oslov
    1.04
    atch
    1.01
    anski
    0.99
    arin
    0.98
     Leone
    0.93
    acist
    0.92
    riter
    0.92
    atic
    0.88
    atches
    0.87
    Activations Density 0.005%

    No Known Activations