© 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. 26588
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the suffix "itz" in various 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
    314
    +0.13
    0.6%
    494
    +0.12
    0.6%
    526
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.03
    700
    +0.12
    0.02
    314
    +0.12
    -0.00
    Negative Logits
    selves
    -0.66
    iety
    -0.66
    ACTED
    -0.64
     NCT
    -0.64
     Pradesh
    -0.63
    åŃ
    -0.63
     occas
    -0.61
     offence
    -0.61
     warranties
    -0.60
     Kamp
    -0.60
    POSITIVE LOGITS
    gerald
    1.75
    patrick
    1.28
    sch
    1.19
    ky
    1.14
    aic
    1.07
    enegger
    1.04
    kies
    1.02
    ki
    1.01
    arella
    1.00
    hou
    0.96
    Activations Density 0.191%

    No Known Activations