© 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. 31473
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with "With" followed by various additional details

    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
    766
    +0.12
    0.6%
    618
    +0.09
    0.4%
    122
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.06
    60
    +0.09
    0.05
    608
    +0.09
    0.04
    Negative Logits
    hyde
    -0.81
    76561
    -0.65
     uncond
    -0.64
     inflic
    -0.61
    ó
    -0.60
    :#
    -0.58
     enthusi
    -0.57
     alleges
    -0.57
    ];
    -0.56
    ogie
    -0.55
    POSITIVE LOGITS
     hindsight
    1.25
    draw
    1.04
     apologies
    1.02
     luck
    1.00
     careful
    0.85
    drawn
    0.83
     exception
    0.82
     enough
    0.79
     proper
    0.78
    stand
    0.78
    Activations Density 0.242%

    No Known Activations