© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    all variations and mentions of the name "Ros."

    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
    526
    +0.15
    0.7%
    286
    +0.13
    0.6%
    84
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.15
    0.02
    286
    +0.13
    0.02
    744
    +0.12
    0.01
    Negative Logits
     Predator
    -0.66
    ORN
    -0.63
     BM
    -0.62
     Blazers
    -0.61
    ously
    -0.61
     Staples
    -0.59
     Quit
    -0.57
     Imp
    -0.56
     Pearce
    -0.56
     Combine
    -0.56
    POSITIVE LOGITS
    etta
    1.17
    alez
    1.13
    coe
    1.07
    kies
    0.99
    enthal
    0.96
    ario
    0.96
    etooth
    0.94
    acea
    0.94
    atom
    0.94
    icky
    0.90
    Activations Density 0.056%

    No Known Activations