© 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. 4267
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of being open or operational, particularly in the context of shelters, businesses, and community services

    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
    295
    +0.12
    0.6%
    677
    +0.11
    0.5%
    609
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.12
    0.06
    295
    +0.11
    0.04
    665
    +0.10
    0.05
    Negative Logits
    Catalog
    -0.69
    odan
    -0.63
    Pac
    -0.63
    ETF
    -0.62
    DOS
    -0.61
    org
    -0.60
    vec
    -0.60
    ĺħ
    -0.60
    doi
    -0.59
    BTC
    -0.59
    POSITIVE LOGITS
     Sundays
    1.06
     Fridays
    1.02
     weekends
    1.01
     Mondays
    1.00
     curfew
    1.00
     Thurs
    0.98
     Tues
    0.96
     weekday
    0.95
     Saturdays
    0.90
    aturdays
    0.80
    Activations Density 0.326%

    No Known Activations