© 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. 10-RES_POST_32K-OAI
    11. 27895
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "on [date]" or "on [number]"

    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
    384
    +0.10
    0.4%
    390
    +0.10
    0.4%
    588
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.10
    0.07
    184
    +0.10
    0.04
    121
    +0.10
    0.06
    Negative Logits
    ãĤ¦ãĤ¹
    -0.76
     somew
    -0.64
    ographically
    -0.63
     americ
    -0.63
     assum
    -0.62
     Protector
    -0.61
    peat
    -0.61
     rightful
    -0.60
    76561
    -0.59
     murd
    -0.56
    POSITIVE LOGITS
     Wednesday
    1.64
     Tuesday
    1.62
     Thursday
    1.60
     Monday
    1.58
     Friday
    1.50
     Sunday
    1.38
     Saturday
    1.34
    Wednesday
    1.29
    Monday
    1.27
    Tuesday
    1.21
    Activations Density 0.480%

    No Known Activations