© 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. 4321
    Prev
    Next
    INDEX
    Explanations

    instances of various objects and belongings in a setting

    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
    591
    +0.11
    0.5%
    558
    +0.11
    0.5%
    249
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.11
    0.04
    39
    +0.11
    0.09
    652
    +0.10
    0.08
    Negative Logits
    thro
    -0.84
    twitch
    -0.79
    zai
    -0.78
     wavelength
    -0.74
     Progressive
    -0.74
    iannopoulos
    -0.73
     Miko
    -0.70
     audiences
    -0.69
     adaptation
    -0.68
     vocal
    -0.68
    POSITIVE LOGITS
     stash
    1.43
     belongings
    1.35
     treasures
    1.28
     looted
    1.27
     luggage
    1.27
     suitcase
    1.19
     souven
    1.18
     items
    1.17
     trove
    1.14
     crates
    1.13
    Activations Density 6.616%

    No Known Activations