© 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. 10-RES_POST_32K-OAI
    11. 30751
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurement or degree of intensity

    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
    718
    +0.11
    0.5%
    519
    +0.09
    0.4%
    657
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.11
    0.04
    331
    +0.09
    0.03
    13
    +0.09
    0.03
    Negative Logits
    endi
    -0.76
    arios
    -0.70
    oslav
    -0.65
    idents
    -0.63
     Associates
    -0.63
    otaur
    -0.62
    urb
    -0.61
     citiz
    -0.61
    itles
    -0.61
     Tsukuyomi
    -0.60
    POSITIVE LOGITS
     fun
    1.11
     shorthand
    0.85
     fodder
    0.84
    ching
    0.76
     annoyance
    0.74
     bother
    0.72
     filler
    0.71
     blasphemy
    0.71
     sore
    0.70
     hassle
    0.69
    Activations Density 0.370%

    No Known Activations