© 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. 7204
    Prev
    Next
    INDEX
    Explanations

    references to legal or institutional settings

    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
    314
    +0.10
    0.4%
    88
    +0.10
    0.4%
    594
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.08
    575
    +0.10
    0.07
    762
    +0.09
    0.06
    Negative Logits
    zes
    -0.69
     Index
    -0.65
    herer
    -0.64
    anon
    -0.63
    iom
    -0.63
    ï¸ı
    -0.62
    ariat
    -0.61
    malink
    -0.60
    insula
    -0.58
     Kickstarter
    -0.58
    POSITIVE LOGITS
     unnoticed
    0.82
    rooms
    0.77
    aturdays
    0.76
    successfully
    0.76
     circles
    0.75
     undet
    0.73
     exting
    0.70
     lobb
    0.68
    speak
    0.64
     assemblies
    0.60
    Activations Density 0.519%

    No Known Activations