© 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 EvalsExportsAPI 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. 28548
    Prev
    Next
    INDEX
    Explanations

    words related to names and locations, particularly of places and people

    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
    303
    +0.12
    0.6%
    659
    +0.12
    0.5%
    441
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.12
    232
    +0.12
    0.11
    314
    +0.11
    -0.00
    Negative Logits
    geoning
    -0.65
     ladies
    -0.64
    ttes
    -0.63
     Thumbnails
    -0.62
    JECT
    -0.60
    selves
    -0.60
     WAY
    -0.60
     disguise
    -0.57
     EE
    -0.57
    wcs
    -0.57
    POSITIVE LOGITS
    ofer
    0.99
    oub
    0.96
    olt
    0.96
    ava
    0.94
    bek
    0.89
    oba
    0.88
    amar
    0.86
    akov
    0.85
    avan
    0.85
    ippy
    0.84
    Activations Density 1.026%

    No Known Activations