© 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. 29197
    Prev
    Next
    INDEX
    Explanations

    terms related to data storage and memory components

    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
    430
    +0.13
    0.6%
    683
    +0.11
    0.5%
    586
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.13
    0.03
    232
    +0.11
    0.04
    145
    +0.10
    0.03
    Negative Logits
    eers
    -1.01
    yip
    -0.97
    eer
    -0.93
    ERN
    -0.80
    eering
    -0.73
    erous
    -0.70
    rade
    -0.70
     Pose
    -0.69
    ulus
    -0.68
    riad
    -0.66
    POSITIVE LOGITS
    IVER
    1.07
    adeon
    0.99
    IVERS
    0.98
    IVE
    0.96
    ifter
    0.94
    IFT
    0.92
    inking
    0.90
    inks
    0.90
    agons
    0.88
    ums
    0.87
    Activations Density 0.113%

    No Known Activations