© 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. 29629
    Prev
    Next
    INDEX
    Explanations

    terminology associated with arrest and release from custody

    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
    665
    +0.11
    0.5%
    373
    +0.10
    0.5%
    222
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.06
    241
    +0.10
    0.05
    761
    +0.10
    0.05
    Negative Logits
    Fit
    -0.73
    asio
    -0.72
     Echoes
    -0.69
    natureconservancy
    -0.66
    ãĤ¦ãĤ¹
    -0.65
     Gears
    -0.65
     sourcing
    -0.64
     hypotheses
    -0.63
    rics
    -0.61
    asin
    -0.61
    POSITIVE LOGITS
     uncond
    1.03
     home
    1.01
     alive
    0.93
     indefinitely
    0.91
    home
    0.89
    enced
    0.89
     pending
    0.87
    prison
    0.87
     prisoner
    0.86
     handcuffed
    0.83
    Activations Density 0.304%

    No Known Activations