© 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. 8-RES_POST_32K-OAI
    11. 6953
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    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
    258
    +0.11
    0.5%
    71
    +0.11
    0.5%
    604
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.11
    0.05
    424
    +0.11
    0.04
    131
    +0.11
    0.04
    Negative Logits
    ãĥij
    -0.60
     prophes
    -0.59
    atin
    -0.57
    ranean
    -0.55
    ufact
    -0.55
    ainment
    -0.55
    aunted
    -0.55
    icent
    -0.54
    ËĪ
    -0.53
    Narr
    -0.53
    POSITIVE LOGITS
     :)
    0.76
    =-=-=-=-=-=-=-=-
    0.72
    udos
    0.72
    Done
    0.71
    ----------------------------------------------------------------
    0.71
     diligence
    0.69
    =-=-=-=-
    0.68
    thanks
    0.68
    !
    0.67
    !!!!!
    0.67
    Activations Density 0.388%

    No Known Activations