© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29668
    Prev
    Next
    INDEX
    Explanations

    references to medals and awards

    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
    168
    +0.14
    0.6%
    490
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.14
    0.02
    575
    +0.11
    0.02
    78
    +0.10
    0.01
    Negative Logits
    rir
    -0.82
    olves
    -0.75
    yll
    -0.68
    lus
    -0.67
    llor
    -0.66
    apest
    -0.66
    iannopoulos
    -0.66
    document
    -0.66
     abdom
    -0.65
    apeake
    -0.65
    POSITIVE LOGITS
     awarded
    0.98
     medal
    0.89
     worn
    0.88
    istry
    0.85
     medals
    0.84
     holder
    0.83
    ific
    0.82
     ceremonies
    0.81
     bearer
    0.77
     badges
    0.75
    Activations Density 0.157%

    No Known Activations