© 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. 29069
    Prev
    Next
    INDEX
    Explanations

    occurrences of vote counts or ratings associated with different entries

    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
    442
    +0.24
    1.2%
    314
    +0.18
    0.9%
    107
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.24
    0.08
    442
    +0.18
    0.10
    316
    +0.17
    0.08
    Negative Logits
     Tsukuyomi
    -0.85
     squid
    -0.83
     cyan
    -0.80
     shutter
    -0.80
     amber
    -0.78
     silhouette
    -0.78
     Dim
    -0.77
     scan
    -0.77
     2
    -0.76
     Beam
    -0.76
    POSITIVE LOGITS
    Fel
    1.25
    Georg
    1.23
    Appearances
    1.21
    feat
    1.19
    paralle
    1.19
    ãĤ´
    1.18
    Moh
    1.18
    Suggest
    1.18
    Coll
    1.18
    Gaza
    1.17
    Activations Density 0.326%

    No Known Activations