© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4634
    Prev
    Next
    INDEX
    Explanations

    statistical data related to crime rates and ownership statistics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    548
    +0.11
    0.5%
    122
    +0.10
    0.5%
    371
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.11
    0.11
    616
    +0.10
    0.08
    408
    +0.10
    0.12
    Negative Logits
     Mous
    -0.77
    achine
    -0.77
     someday
    -0.75
    iquette
    -0.68
     sane
    -0.68
     hindsight
    -0.67
    config
    -0.66
    Journal
    -0.66
    BTC
    -0.64
    etc
    -0.64
    POSITIVE LOGITS
     outl
    0.77
     inclusion
    0.72
     (%
    0.70
     omission
    0.69
     (%)
    0.68
     declines
    0.68
    ridor
    0.67
     exclus
    0.66
    uties
    0.66
    ocations
    0.65
    Activations Density 2.263%

    No Known Activations