© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4518
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms related to biological or medical concepts

    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
    728
    +0.11
    0.5%
    735
    +0.09
    0.4%
    675
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.11
    0.14
    439
    +0.09
    0.11
    759
    +0.09
    0.11
    Negative Logits
    ãĥ³ãĤ¸
    -0.64
    enegger
    -0.61
    bra
    -0.60
    ãĥ£
    -0.60
    cheon
    -0.59
    POL
    -0.59
     coli
    -0.59
    ticket
    -0.57
    sonian
    -0.55
    IOR
    -0.55
    POSITIVE LOGITS
    ivably
    0.63
    ciation
    0.63
    eq
    0.63
    enza
    0.62
    γ
    0.61
    iguous
    0.61
    athering
    0.61
    ippi
    0.59
    cation
    0.58
     Okawaru
    0.58
    Activations Density 0.800%

    No Known Activations