© 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. 29776
    Prev
    Next
    INDEX
    Explanations

    mentions of films, movies, or shows within the text

    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
    373
    +0.13
    0.6%
    563
    +0.10
    0.5%
    160
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    563
    +0.13
    0.08
    288
    +0.10
    0.08
    401
    +0.10
    0.08
    Negative Logits
    ————
    -0.73
    Ô
    -0.73
     guiName
    -0.72
    actionDate
    -0.70
    ????????
    -0.68
    soever
    -0.67
    DragonMagazine
    -0.66
     +++
    -0.64
    ntil
    -0.64
    ECA
    -0.61
    POSITIVE LOGITS
     itself
    1.24
    's
    1.16
     succeeds
    0.89
     lacks
    0.88
    runners
    0.87
     encourages
    0.86
     relies
    0.85
     progresses
    0.84
     employs
    0.84
    wright
    0.84
    Activations Density 0.481%

    No Known Activations