© 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. 26245
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of parasitism

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    464
    +0.13
    0.6%
    284
    +0.12
    0.5%
    662
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.08
    232
    +0.12
    0.09
    659
    +0.11
    0.08
    Negative Logits
    KEN
    -0.80
    DEN
    -0.70
     STORY
    -0.68
    DAY
    -0.68
    Ô
    -0.67
    GBT
    -0.66
    hower
    -0.63
     eyed
    -0.63
     hiking
    -0.62
     WWF
    -0.62
    POSITIVE LOGITS
    inus
    1.74
    orum
    1.70
    atus
    1.67
    icum
    1.56
    icus
    1.51
    atis
    1.50
    um
    1.49
    arius
    1.48
    anus
    1.48
    ius
    1.48
    Activations Density 1.005%

    No Known Activations