© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26575
    Prev
    Next
    INDEX
    Explanations

    terms related to online trolling and abusive behavior

    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
    408
    +0.13
    0.6%
    420
    +0.12
    0.5%
    47
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.13
    0.23
    362
    +0.12
    0.21
    408
    +0.10
    0.22
    Negative Logits
     [+
    -0.91
     ?)
    -0.84
    starter
    -0.82
     :(
    -0.81
    /(
    -0.78
     ðŁĺ
    -0.78
     Anyway
    -0.76
    inventoryQuantity
    -0.76
    /)
    -0.75
     :-)
    -0.73
    POSITIVE LOGITS
     countless
    1.36
     myriad
    1.33
     innumerable
    1.23
     unsuspecting
    1.16
     disparate
    1.16
     dozens
    1.14
     relentlessly
    1.12
     tirelessly
    1.09
     unimaginable
    1.07
     endless
    1.06
    Activations Density 4.614%

    No Known Activations