© 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. 24194
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly states and cities

    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
    481
    +0.22
    1.0%
    219
    +0.12
    0.5%
    412
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.22
    0.05
    412
    +0.12
    0.04
    488
    +0.10
    0.04
    Negative Logits
    thood
    -0.75
    ãĥīãĥ©
    -0.71
    imon
    -0.70
    sbm
    -0.68
    BILITIES
    -0.67
    umbledore
    -0.66
    xon
    -0.64
    Cert
    -0.61
    ="/
    -0.61
     Emails
    -0.60
    POSITIVE LOGITS
     periphery
    1.05
     economy
    0.92
     vicinity
    0.91
     centre
    0.88
     skyline
    0.85
     electorate
    0.84
     outskirts
    0.83
     populace
    0.81
     area
    0.80
     illegally
    0.79
    Activations Density 0.124%

    No Known Activations