© 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. 10-RES_POST_32K-OAI
    11. 32025
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Bar" followed by a number or title

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    728
    +0.09
    0.4%
    390
    +0.09
    0.4%
    220
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.03
    232
    +0.09
    0.03
    314
    +0.09
    0.00
    Negative Logits
    mercial
    -0.67
    matically
    -0.67
    mable
    -0.67
     FANTASY
    -0.66
     darts
    -0.62
    ãĤĭ
    -0.61
     detector
    -0.60
    swer
    -0.59
     overtake
    -0.59
    GMT
    -0.59
    POSITIVE LOGITS
    uch
    0.96
    becue
    0.95
    low
    0.93
    aq
    0.92
    ret
    0.85
    aka
    0.84
    rera
    0.83
    rage
    0.81
    bour
    0.80
    athe
    0.78
    Activations Density 0.219%

    No Known Activations