© 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. 8-RES_POST_32K-OAI
    11. 8903
    Prev
    Next
    INDEX
    Explanations

    references to structural aspects of urban and societal organization

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    258
    +0.12
    0.5%
    728
    +0.10
    0.5%
    641
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.12
    0.19
    159
    +0.10
    0.08
    362
    +0.09
    0.09
    Negative Logits
     phantom
    -0.76
     unheard
    -0.76
     goodies
    -0.70
     reminder
    -0.69
     specials
    -0.69
     rites
    -0.69
     initials
    -0.68
     rite
    -0.68
     pecul
    -0.67
     haun
    -0.67
    POSITIVE LOGITS
    hent
    0.85
    cms
    0.85
    abase
    0.76
    uitive
    0.74
     Gutenberg
    0.72
    given
    0.72
    esan
    0.69
    consumer
    0.69
     typical
    0.69
    traditional
    0.68
    Activations Density 0.651%

    No Known Activations