© 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 EvalsExportsAPI 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. 30956
    Prev
    Next
    INDEX
    Explanations

    the repeated mention of the name "Sid" and its variations in different contexts

    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
    299
    +0.12
    0.6%
    423
    +0.10
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    314
    +0.10
    -0.00
    588
    +0.10
    0.01
    Negative Logits
    inately
    -0.71
     retard
    -0.64
     magnets
    -0.61
     largeDownload
    -0.60
    AUT
    -0.57
     arms
    -0.57
    eff
    -0.56
    ruits
    -0.56
    united
    -0.55
    aeda
    -0.55
    POSITIVE LOGITS
    eways
    1.60
    etr
    1.30
    este
    1.25
    eline
    1.21
    ew
    1.14
    eport
    1.11
    ewater
    1.09
    est
    1.02
     Meier
    1.02
    elines
    0.95
    Activations Density 0.078%

    No Known Activations