© 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. 24310
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating the act of living or residing in a location

    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
    152
    +0.12
    0.6%
    39
    +0.11
    0.5%
    132
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.12
    0.03
    39
    +0.11
    0.03
    152
    +0.11
    0.03
    Negative Logits
    elight
    -0.79
    iasis
    -0.75
    xual
    -0.75
    aptic
    -0.70
    oug
    -0.67
    ause
    -0.66
    umbs
    -0.65
    vernment
    -0.65
    aneous
    -0.64
    selage
    -0.64
    POSITIVE LOGITS
     upstairs
    1.01
     downstairs
    0.98
     paycheck
    0.89
     nearby
    0.89
    chool
    0.89
     vic
    0.85
     abroad
    0.79
     downtown
    0.77
    house
    0.77
    stead
    0.76
    Activations Density 0.031%

    No Known Activations