© 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. 32666
    Prev
    Next
    INDEX
    Explanations

    research findings related to the effectiveness and shortcomings of medical studies

    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
    329
    +0.11
    0.5%
    540
    +0.10
    0.5%
    133
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.11
    0.14
    329
    +0.10
    0.11
    661
    +0.09
    0.07
    Negative Logits
    planet
    -0.79
    atron
    -0.72
     Optimus
    -0.70
     Terminal
    -0.69
     Celt
    -0.69
    Planet
    -0.68
    jriwal
    -0.68
    ãĥķãĤ©
    -0.66
    terday
    -0.66
    erenn
    -0.65
    POSITIVE LOGITS
     randomized
    1.40
     study
    1.38
    Study
    1.38
     observational
    1.33
     studies
    1.27
     longitudinal
    1.26
     cohort
    1.25
    study
    1.24
     sample
    1.18
     Study
    1.17
    Activations Density 6.487%

    No Known Activations