© 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. 32059
    Prev
    Next
    INDEX
    Explanations

    phrases that express increased ease or simplicity in various contexts

    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
    51
    +0.16
    0.7%
    491
    +0.13
    0.6%
    490
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.16
    0.05
    42
    +0.13
    0.04
    737
    +0.11
    0.04
    Negative Logits
    pend
    -0.73
    bris
    -0.69
    lings
    -0.65
     Difference
    -0.65
     Goo
    -0.64
     Tsukuyomi
    -0.61
    liest
    -0.60
    ãĤ¦ãĤ¹
    -0.59
    leys
    -0.58
    fulness
    -0.57
    POSITIVE LOGITS
     said
    1.10
     described
    0.83
     explained
    0.83
    said
    0.81
     talked
    0.81
     thanked
    0.80
     argued
    0.74
     stated
    0.74
     joked
    0.73
     handled
    0.72
    Activations Density 0.259%

    No Known Activations