© 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. 6644
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity or relational context

    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
    709
    +0.15
    0.7%
    463
    +0.13
    0.6%
    25
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.15
    0.04
    192
    +0.13
    0.03
    25
    +0.10
    0.04
    Negative Logits
     Aires
    -0.57
     nominate
    -0.56
     prod
    -0.55
     marginal
    -0.54
     earthqu
    -0.54
     cope
    -0.52
    ¥ŀ
    -0.51
     redes
    -0.51
     banner
    -0.50
     sear
    -0.50
    POSITIVE LOGITS
    -
    1.14
    tenance
    1.05
    lihood
    1.04
    -$
    1.02
    etheless
    0.97
    -'
    0.97
    _-_
    0.94
    -[
    0.93
    /)
    0.90
    usterity
    0.89
    Activations Density 0.218%

    No Known Activations