© 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. 29486
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to various fields such as media, healthcare, and programming

    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
    256
    +0.13
    0.6%
    165
    +0.12
    0.5%
    536
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.13
    0.25
    691
    +0.12
    0.16
    575
    +0.10
    0.22
    Negative Logits
     «
    -0.65
    surprisingly
    -0.55
    ËĪ
    -0.54
    bably
    -0.54
    ĪĴ
    -0.50
    ãĥ¯ãĥ³
    -0.50
    xtap
    -0.50
    ailability
    -0.49
    arnaev
    -0.47
    ¿½
    -0.46
    POSITIVE LOGITS
    .")
    2.44
    ").
    2.33
    ".
    2.30
    ",
    2.28
    ";
    2.27
    %"
    2.25
    "
    2.23
    "?
    2.23
    "—
    2.21
    )"
    2.19
    Activations Density 18.668%

    No Known Activations