© 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. 27854
    Prev
    Next
    INDEX
    Explanations

    references to the concept of rest or relaxation

    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
    314
    +0.16
    0.7%
    557
    +0.13
    0.6%
    560
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    557
    +0.16
    0.02
    560
    +0.13
    0.01
    416
    +0.11
    0.01
    Negative Logits
    女
    -0.70
    sha
    -0.68
     NEWS
    -0.61
    vernment
    -0.60
     Strait
    -0.59
     Parade
    -0.57
     Centauri
    -0.57
     Sapphire
    -0.57
     tease
    -0.57
    gee
    -0.56
    POSITIVE LOGITS
    ructure
    1.40
    orative
    1.23
    ock
    1.21
    raint
    1.17
     assured
    1.09
    arts
    1.07
    raints
    1.05
    ocking
    1.05
    itution
    0.99
    ricting
    0.97
    Activations Density 0.061%

    No Known Activations