© 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. 10-RES_POST_32K-OAI
    6. 29663
    Prev
    Next
    INDEX
    Explanations

    textual elements and formatting within a document

    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
    512
    +0.12
    0.6%
    101
    +0.10
    0.5%
    603
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.12
    0.02
    720
    +0.10
    0.03
    452
    +0.09
    0.01
    Negative Logits
    SPONSORED
    -0.68
    hematic
    -0.62
    Cath
    -0.61
    Done
    -0.61
    aido
    -0.61
    ãĤ¹ãĥĪ
    -0.60
    ãĥīãĥ©
    -0.60
    Fake
    -0.59
    Cop
    -0.59
    Tam
    -0.59
    POSITIVE LOGITS
    \":
    0.84
    =>
    0.80
     =>
    0.79
    llah
    0.77
    =\"
    0.76
     "#
    0.75
    ":"
    0.74
     "$:/
    0.70
     ``
    0.64
     EntityItem
    0.62
    Activations Density 0.207%

    No Known Activations