© 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. 29330
    Prev
    Next
    INDEX
    Explanations

    numeric values and dimensions

    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
    +0.10
    0.5%
    420
    +0.10
    0.5%
    361
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    701
    +0.10
    0.01
    316
    +0.09
    0.01
    Negative Logits
    emale
    -0.80
    agonist
    -0.73
    osate
    -0.66
    achev
    -0.63
    ¬¼
    -0.60
    £ı
    -0.60
    comings
    -0.59
    FORMATION
    -0.58
    edge
    -0.57
    represent
    -0.57
    POSITIVE LOGITS
    ":"
    0.69
     ..........
    0.68
    },"
    0.63
     "$:/
    0.61
     blur
    0.59
     caption
    0.58
    ãģ®å
    0.57
     <<
    0.57
     pont
    0.57
     Neh
    0.55
    Activations Density 0.108%

    No Known Activations