© 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. 27943
    Prev
    Next
    INDEX
    Explanations

    terms related to causation and accountability

    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
    +0.22
    1.0%
    756
    +0.13
    0.6%
    88
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    696
    +0.22
    0.09
    566
    +0.13
    0.07
    314
    +0.10
    -0.04
    Negative Logits
     Mate
    -0.70
     Tile
    -0.66
     Anon
    -0.65
     Balk
    -0.64
     Buk
    -0.64
     Turk
    -0.61
     Skydragon
    -0.61
     virgin
    -0.61
     Wake
    -0.60
     Constantin
    -0.60
    POSITIVE LOGITS
    :(
    0.94
    hesda
    0.80
    APS
    0.78
    quarters
    0.77
    mosp
    0.77
    have
    0.76
    Bet
    0.76
    :,
    0.74
    iculty
    0.74
    withstanding
    0.74
    Activations Density 2.839%

    No Known Activations