© 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. 8-RES_POST_32K-OAI
    11. 8395
    Prev
    Next
    INDEX
    Explanations

    the name "Roy" in various contexts

    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
    238
    +0.10
    0.5%
    316
    +0.10
    0.4%
    496
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    682
    +0.10
    0.02
    659
    +0.10
    0.02
    326
    +0.10
    0.02
    Negative Logits
     Despair
    -0.62
     gestation
    -0.60
    iphany
    -0.60
     opacity
    -0.59
    entimes
    -0.58
     Situation
    -0.58
    iest
    -0.58
    ocalypse
    -0.58
     TSA
    -0.58
    afer
    -0.57
    POSITIVE LOGITS
    alties
    1.53
    ce
    1.06
    croft
    0.95
    hips
    0.91
    ski
    0.88
    bal
    0.85
    ston
    0.77
    din
    0.77
    als
    0.76
    geon
    0.76
    Activations Density 0.114%

    No Known Activations