© 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. 27591
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal issues and controversies

    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
    33
    +0.10
    0.5%
    354
    +0.10
    0.4%
    434
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.10
    0.14
    86
    +0.10
    0.09
    724
    +0.09
    0.12
    Negative Logits
    ]."
    -1.30
    !".
    -1.20
    '>
    -1.18
    >.
    -1.11
    '.
    -1.09
    "/>
    -1.08
    \">
    -1.07
    ?".
    -1.03
    '."
    -1.00
    }.
    -1.00
    POSITIVE LOGITS
    ,''
    1.63
    ,"
    1.55
    .,"
    1.35
    ),"
    1.32
     ,"
    1.30
    ,'"
    1.08
    ',"
    0.93
    ,'
    0.92
     ...
    0.92
    ],"
    0.81
    Activations Density 2.632%

    No Known Activations