© 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. 29312
    Prev
    Next
    INDEX
    Explanations

    elements related to question and answer (Q&A) formats in conversations

    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
    373
    +0.11
    0.5%
    9
    +0.10
    0.5%
    437
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.11
    0.01
    97
    +0.10
    0.01
    357
    +0.09
    0.01
    Negative Logits
    heed
    -0.86
    ufact
    -0.78
    hower
    -0.72
    netflix
    -0.69
    gins
    -0.65
    illac
    -0.64
    raint
    -0.63
    fitted
    -0.62
    oreal
    -0.62
     endif
    -0.62
    POSITIVE LOGITS
    reply
    0.87
    FAQ
    0.75
    A
    0.73
    qs
    0.72
    Answer
    0.72
    LD
    0.70
    Q
    0.70
    oS
    0.69
    RC
    0.69
    Discuss
    0.68
    Activations Density 0.109%

    No Known Activations