© 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. 10-RES_POST_32K-OAI
    11. 29490
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, likely characters or people in a narrative context

    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
    289
    +0.14
    0.6%
    437
    +0.14
    0.6%
    740
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.02
    289
    +0.14
    0.01
    314
    +0.12
    -0.00
    Negative Logits
    doms
    -0.78
    ttes
    -0.71
    lasses
    -0.69
    bably
    -0.64
    ELD
    -0.64
    JECT
    -0.64
    ufact
    -0.62
    ntil
    -0.61
    dom
    -0.61
    lass
    -0.61
    POSITIVE LOGITS
    andra
    1.15
    ettes
    1.14
    ette
    1.08
    idy
    1.07
    ady
    0.96
    ava
    0.96
    iop
    0.95
    iano
    0.94
    aign
    0.93
    iod
    0.90
    Activations Density 0.061%

    No Known Activations