© 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. 26916
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases conveying strong emotions or reactions

    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
    506
    +0.10
    0.5%
    18
    +0.10
    0.5%
    253
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.10
    0.04
    572
    +0.10
    0.07
    449
    +0.10
    0.04
    Negative Logits
     preferably
    -0.74
    etheless
    -0.67
    theless
    -0.67
     likewise
    -0.66
    problem
    -0.64
    cific
    -0.64
    wcsstore
    -0.64
    isSpecialOrderable
    -0.64
     peacefully
    -0.64
     optionally
    -0.64
    POSITIVE LOGITS
    !!
    0.80
    !!!!!!!!
    0.80
    !!!!!
    0.78
    !!!!
    0.76
    Wow
    0.75
    !!!
    0.75
    oooooooooooooooo
    0.69
    !
    0.66
    eeee
    0.64
    !]
    0.64
    Activations Density 1.601%

    No Known Activations