© 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. 8-RES_POST_32K-OAI
    11. 6726
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    571
    +0.13
    0.6%
    605
    +0.10
    0.5%
    98
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.13
    0.08
    566
    +0.10
    0.06
    571
    +0.10
    0.06
    Negative Logits
    ById
    -0.68
    burgh
    -0.61
     Parables
    -0.61
    oute
    -0.61
    aneous
    -0.60
    OUP
    -0.58
    urrection
    -0.58
     Complete
    -0.57
    pmwiki
    -0.57
     Memor
    -0.55
    POSITIVE LOGITS
    tains
    0.62
    é¾įå¥ij士
    0.61
    .</
    0.60
     risking
    0.60
    utm
    0.60
     ever
    0.59
     accidentally
    0.59
    !.
    0.59
    .",
    0.59
    endi
    0.57
    Activations Density 1.135%

    No Known Activations