© 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. 32564
    Prev
    Next
    INDEX
    Explanations

    the conjunction "But" indicating a contrast or shift in the narrative

    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
    364
    +0.13
    0.6%
    501
    +0.12
    0.5%
    69
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.13
    0.09
    8
    +0.12
    0.06
    203
    +0.11
    0.05
    Negative Logits
     Retrieved
    -0.82
    dayName
    -0.78
    SourceFile
    -0.76
    Thumbnail
    -0.72
     CLSID
    -0.71
    ())
    -0.68
    irms
    -0.66
     ())
    -0.66
     Annotations
    -0.66
     Definitely
    -0.64
    POSITIVE LOGITS
     despite
    1.01
     amid
    1.00
     while
    0.96
    rea
    0.91
    chers
    0.86
     whereas
    0.85
     unlike
    0.82
    while
    0.81
     critics
    0.81
    withstanding
    0.81
    Activations Density 0.261%

    No Known Activations