© 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. 29067
    Prev
    Next
    INDEX
    Explanations

    time-related timestamps and identifiers, particularly involving dates and times

    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
    267
    +0.16
    0.7%
    373
    +0.13
    0.6%
    131
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.16
    0.02
    6
    +0.13
    0.02
    561
    +0.11
    0.01
    Negative Logits
    Attempts
    -0.89
    æ©
    -0.88
    foreseen
    -0.84
    ãĥ¢
    -0.76
    pole
    -0.74
    condition
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.74
    SPONSORED
    -0.73
    âĶĢâĶĢâĶĢâĶĢ
    -0.73
    Narr
    -0.72
    POSITIVE LOGITS
     Quote
    1.07
     Nice
    1.06
     Sounds
    1.05
     Awesome
    1.01
     Looks
    1.00
     Seems
    0.98
     Wow
    0.96
     Alright
    0.95
     Interesting
    0.94
     Yeah
    0.93
    Activations Density 0.082%

    No Known Activations