© 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. 8-RES_POST_32K-OAI
    11. 8671
    Prev
    Next
    INDEX
    Explanations

    the letter "p" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    504
    +0.14
    0.6%
    578
    +0.12
    0.6%
    655
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.14
    0.06
    482
    +0.12
    0.06
    648
    +0.12
    0.06
    Negative Logits
    EST
    -0.82
    ELS
    -0.78
    EC
    -0.77
    EMP
    -0.76
    ARI
    -0.76
    姫
    -0.75
    NESS
    -0.75
    IFA
    -0.72
    ĪĴ
    -0.71
    eer
    -0.71
    POSITIVE LOGITS
    okemon
    0.99
    urchase
    0.93
    cs
    0.91
    ending
    0.85
    ossible
    0.82
    oké
    0.81
    aul
    0.80
    interest
    0.80
    iscopal
    0.80
    ansas
    0.80
    Activations Density 0.158%

    No Known Activations