© 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. 29193
    Prev
    Next
    INDEX
    Explanations

    terms related to booking and reservations

    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
    500
    +0.12
    0.6%
    10
    +0.10
    0.5%
    726
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.12
    0.03
    222
    +0.10
    0.03
    288
    +0.10
    0.04
    Negative Logits
    utenberg
    -0.77
     Flavoring
    -0.74
    acea
    -0.73
     actionGroup
    -0.70
    baugh
    -0.70
    ModLoader
    -0.68
    warts
    -0.68
    ppa
    -0.67
    ritis
    -0.66
    rity
    -0.66
    POSITIVE LOGITS
     reservations
    1.09
     booked
    1.05
     booking
    1.03
     appointments
    0.89
     reservation
    0.88
     appointment
    0.85
     fee
    0.83
     fees
    0.79
     Reserv
    0.79
    ointment
    0.78
    Activations Density 0.292%

    No Known Activations