© 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. 10-RES_POST_32K-OAI
    11. 29072
    Prev
    Next
    INDEX
    Explanations

    equality signs in mathematical expressions or equations

    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
    160
    +0.16
    0.7%
    314
    +0.15
    0.7%
    107
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.16
    0.02
    160
    +0.15
    0.04
    284
    +0.12
    0.03
    Negative Logits
     breed
    -0.77
     pointing
    -0.75
     wrinkles
    -0.73
     undercut
    -0.70
     releg
    -0.70
     coat
    -0.69
     Reserv
    -0.67
     distribut
    -0.67
     limp
    -0.67
     superf
    -0.67
    POSITIVE LOGITS
    False
    1.42
    True
    1.31
    None
    1.28
    ãĥīãĥ©ãĤ´ãĥ³
    1.25
    ãĥ´ãĤ¡
    1.23
    true
    1.21
    TR
    1.20
    yes
    1.17
    false
    1.15
    PsyNetMessage
    1.13
    Activations Density 0.141%

    No Known Activations