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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32020
    Prev
    Next
    INDEX
    Explanations

    information related to events or gatherings

    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
    314
    +0.13
    0.6%
    707
    +0.11
    0.5%
    121
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.09
    232
    +0.11
    0.09
    731
    +0.11
    0.03
    Negative Logits
     curses
    -0.83
     verbs
    -0.81
     opacity
    -0.81
     worms
    -0.80
     claws
    -0.80
     inert
    -0.80
     passively
    -0.79
     encryption
    -0.78
     glyph
    -0.77
     decrypt
    -0.77
    POSITIVE LOGITS
    City
    1.66
    city
    1.63
    town
    1.61
    Town
    1.50
     City
    1.35
     Cities
    1.26
    Country
    1.25
    Store
    1.23
    ometown
    1.22
     CITY
    1.21
    Activations Density 1.428%

    No Known Activations