© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5186
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Paul."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.14
    0.6%
    526
    +0.11
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.14
    0.04
    519
    +0.11
    0.03
    200
    +0.09
    0.03
    Negative Logits
     lodge
    -0.67
     tolerant
    -0.64
    QUEST
    -0.59
     Elven
    -0.57
     quot
    -0.56
    SPONSORED
    -0.54
    engineering
    -0.54
     lar
    -0.54
    dayName
    -0.54
     minded
    -0.53
    POSITIVE LOGITS
    ine
    1.13
    sen
    1.08
    son
    1.05
    ozo
    1.02
    sonian
    1.00
     McCartney
    0.94
    sburg
    0.91
    ieu
    0.90
    angelo
    0.88
    ina
    0.88
    Activations Density 0.059%

    No Known Activations