© 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. 28500
    Prev
    Next
    INDEX
    Explanations

    interactions related to comments and subscriptions

    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
    39
    +0.11
    0.5%
    76
    +0.10
    0.4%
    674
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.11
    0.09
    308
    +0.10
    0.05
    595
    +0.10
    0.05
    Negative Logits
    llah
    -0.73
     bodily
    -0.68
    lethal
    -0.67
     conscientious
    -0.64
     coupled
    -0.64
     scripted
    -0.64
     assassin
    -0.63
     confid
    -0.63
     assailant
    -0.63
     theoretically
    -0.62
    POSITIVE LOGITS
     Previous
    1.27
     »
    1.26
     Browse
    1.25
     Search
    1.25
     Subscribe
    1.19
     Submit
    1.19
     Loading
    1.18
     Sort
    1.18
     Cancel
    1.17
     âĢº
    1.16
    Activations Density 1.867%

    No Known Activations