© 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 EvalsExportsAPI 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. 7065
    Prev
    Next
    INDEX
    Explanations

    actions or states of being related to significant activities or events

    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
    101
    +0.12
    0.6%
    496
    +0.12
    0.5%
    64
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.12
    -0.01
    101
    +0.12
    0.13
    464
    +0.11
    0.11
    Negative Logits
    nic
    -0.72
    andal
    -0.63
     Moroc
    -0.62
    ãĥĨãĤ£
    -0.62
     Uni
    -0.56
    classic
    -0.54
     ner
    -0.53
    lear
    -0.53
     NCT
    -0.53
    tone
    -0.53
    POSITIVE LOGITS
    soever
    0.68
    BILITIES
    0.64
     Sabha
    0.63
    lehem
    0.63
     largeDownload
    0.62
     toward
    0.59
    displayText
    0.58
     halted
    0.58
    STON
    0.57
    staking
    0.57
    Activations Density 0.885%

    No Known Activations