© 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. 28457
    Prev
    Next
    INDEX
    Explanations

    the word "may" and its various forms used in the context of permission, possibility, or capability

    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
    459
    +0.15
    0.7%
    525
    +0.11
    0.5%
    261
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.15
    0.06
    49
    +0.11
    0.04
    278
    +0.09
    0.04
    Negative Logits
    gets
    -0.75
     doomed
    -0.69
    alky
    -0.65
    ãĥŀ
    -0.64
    uggest
    -0.64
    sighted
    -0.62
    has
    -0.61
    mallow
    -0.59
    ãĤ§
    -0.59
    pring
    -0.59
    POSITIVE LOGITS
     optionally
    0.88
     lawfully
    0.80
    adesh
    0.68
     freely
    0.67
     reasonably
    0.66
    án
    0.65
    abo
    0.65
     legitimately
    0.64
     alternatively
    0.64
    ADA
    0.64
    Activations Density 0.115%

    No Known Activations