© 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 EvalsExportsinterp-engineNEWAPI 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. 8396
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to technical specifications and classifications

    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
    225
    +0.13
    0.6%
    404
    +0.11
    0.5%
    205
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.10
    232
    +0.11
    0.08
    308
    +0.10
    0.05
    Negative Logits
     carbohyd
    -0.99
    yond
    -0.87
    etheless
    -0.77
    irez
    -0.76
    soDeliveryDate
    -0.75
     captcha
    -0.72
    imil
    -0.71
    icter
    -0.71
    amous
    -0.71
     mosqu
    -0.71
    POSITIVE LOGITS
     Suite
    1.02
     Association
    0.93
     Index
    0.91
    naire
    0.88
    âĦ¢
    0.86
     Examination
    0.83
     Award
    0.82
     Advisor
    0.80
    ®
    0.80
     Simulator
    0.80
    Activations Density 0.813%

    No Known Activations