© 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 49152
    9. 8-RES_FS49152-JB
    11. 25739
    Prev
    Next
    INDEX
    Explanations

    phrases related to situational context, particularly "right place" and "right time."

    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
    459
    +0.12
    0.5%
    255
    +0.12
    0.5%
    649
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.12
    0.02
    737
    +0.12
    0.02
    575
    +0.10
    0.02
    Negative Logits
    limited
    -0.71
    famous
    -0.70
    irl
    -0.70
    naissance
    -0.69
    ipel
    -0.64
    eatures
    -0.64
    amily
    -0.64
    culosis
    -0.63
    teness
    -0.62
    sponsored
    -0.62
    POSITIVE LOGITS
    çĦ
    0.70
     mate
    0.67
    pei
    0.66
     choices
    0.64
    ãĤĬ
    0.64
    nings
    0.63
    ãĤ¹ãĥĪ
    0.63
     etiquette
    0.62
     ingred
    0.61
     curve
    0.61
    Activations Density 0.054%

    No Known Activations