© 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. 31207
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate future actions or intentions

    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
    115
    +0.10
    0.5%
    182
    +0.09
    0.4%
    655
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.15
    718
    +0.09
    0.12
    49
    +0.09
    0.12
    Negative Logits
    yss
    -0.77
     texted
    -0.68
     Chapel
    -0.62
    CHAT
    -0.61
    CHA
    -0.60
     Charm
    -0.59
     Archdemon
    -0.59
     vandal
    -0.59
     Unsure
    -0.58
    aganda
    -0.57
    POSITIVE LOGITS
     discuss
    0.98
    umbn
    0.91
     discussed
    0.89
     enumer
    0.88
     discusses
    0.88
     overview
    0.87
     outline
    0.86
     detail
    0.85
     outlined
    0.84
     covered
    0.83
    Activations Density 0.863%

    No Known Activations