© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4635
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "vast" in contexts related to quantity or extent

    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
    355
    +0.13
    0.6%
    288
    +0.09
    0.4%
    154
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.13
    0.02
    154
    +0.09
    0.02
    573
    +0.08
    0.02
    Negative Logits
    imer
    -0.65
    Dialogue
    -0.64
    headers
    -0.62
    iffe
    -0.60
    earance
    -0.58
    apple
    -0.58
    pered
    -0.57
    annis
    -0.56
    pei
    -0.55
    NEY
    -0.55
    POSITIVE LOGITS
     majority
    1.05
    ness
    0.97
     expans
    0.83
    itud
    0.81
    sword
    0.76
    urous
    0.76
    itudes
    0.75
    entimes
    0.74
     gulf
    0.73
     swath
    0.73
    Activations Density 0.042%

    No Known Activations