© 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. 30013
    Prev
    Next
    INDEX
    Explanations

    references to relationships and connections between entities or concepts

    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
    255
    +0.14
    0.6%
    459
    +0.11
    0.5%
    135
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.14
    0.10
    109
    +0.11
    0.10
    139
    +0.11
    0.09
    Negative Logits
    resa
    -0.84
    Released
    -0.77
     VID
    -0.70
    Yep
    -0.67
     EVER
    -0.67
    anmar
    -0.64
     Written
    -0.64
    Dear
    -0.63
    ãĢİ
    -0.62
     Featured
    -0.62
    POSITIVE LOGITS
     aids
    0.95
     then
    0.92
     facilitates
    0.91
     ordinarily
    0.91
     prevents
    0.89
     might
    0.82
     may
    0.81
     inhibits
    0.81
     helps
    0.80
     normally
    0.80
    Activations Density 0.550%

    No Known Activations