© 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. 27783
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "years" or time intervals

    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
    715
    +0.13
    0.6%
    361
    +0.10
    0.5%
    518
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    715
    +0.13
    0.04
    44
    +0.10
    0.03
    258
    +0.09
    0.04
    Negative Logits
     Cosponsors
    -0.68
     Helpful
    -0.66
    achus
    -0.64
    redients
    -0.64
     Anchorage
    -0.61
    acco
    -0.61
    everyone
    -0.60
     VIDEOS
    -0.60
     Disorder
    -0.60
    hest
    -0.60
    POSITIVE LOGITS
     anniversary
    1.21
     olds
    1.13
     old
    0.96
     itch
    0.94
     countdown
    0.92
     lifespan
    0.92
     reign
    0.91
     span
    0.90
     horizon
    0.85
     cycle
    0.85
    Activations Density 0.103%

    No Known Activations