© 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. 10-RES_POST_32K-OAI
    11. 26866
    Prev
    Next
    INDEX
    Explanations

    expressions related to frustration or disappointment

    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
    517
    +0.11
    0.5%
    450
    +0.10
    0.5%
    34
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.04
    314
    +0.10
    -0.01
    659
    +0.10
    0.03
    Negative Logits
     SPD
    -0.68
     Bubble
    -0.67
     handc
    -0.65
    rings
    -0.63
     Gron
    -0.62
     POV
    -0.62
     Stoke
    -0.61
     CPR
    -0.61
    tsy
    -0.61
     Bowser
    -0.61
    POSITIVE LOGITS
    ils
    1.17
    ava
    1.11
    util
    1.02
    il
    0.98
    appro
    0.97
    erest
    0.96
    app
    0.95
    acqu
    0.94
    avez
    0.94
    une
    0.92
    Activations Density 0.248%

    No Known Activations