© 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. 31104
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sole" or related terms indicating singularity or exclusivity

    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
    616
    +0.10
    0.4%
    457
    +0.10
    0.4%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.10
    0.02
    99
    +0.10
    0.01
    391
    +0.10
    0.01
    Negative Logits
     Hole
    -0.74
     Reloaded
    -0.71
     Everywhere
    -0.68
     Heads
    -0.64
     Faust
    -0.64
     Close
    -0.62
     horm
    -0.62
    hops
    -0.62
     Rising
    -0.62
     Caf
    -0.60
    POSITIVE LOGITS
     propriet
    1.23
    mn
    1.12
     survivor
    1.03
     occupant
    0.98
     purpose
    0.87
     reliance
    0.87
     exception
    0.84
    tenance
    0.83
     inhabit
    0.82
     superpower
    0.81
    Activations Density 0.093%

    No Known Activations