© 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. 10-RES_POST_32K-OAI
    11. 28489
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or forms of the word "its."

    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
    362
    +0.17
    0.8%
    608
    +0.14
    0.6%
    384
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.08
    608
    +0.14
    0.08
    385
    +0.10
    0.06
    Negative Logits
    ocument
    -0.83
    sson
    -0.81
    tsy
    -0.78
    urable
    -0.77
    lund
    -0.77
    ominated
    -0.75
    ":[
    -0.72
    ucket
    -0.70
    etsy
    -0.70
    veland
    -0.69
    POSITIVE LOGITS
     own
    1.71
     namesake
    1.31
     predecessor
    1.28
     entirety
    1.28
     newest
    1.17
     latest
    1.09
     biggest
    1.06
     predecessors
    1.05
     respective
    1.02
     newfound
    1.02
    Activations Density 0.427%

    No Known Activations