© 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. 8-RES_POST_32K-OAI
    11. 6474
    Prev
    Next
    INDEX
    Explanations

    phrases indicating chaos or disorder

    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
    47
    +0.10
    0.5%
    464
    +0.10
    0.5%
    427
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.10
    0
    +0.10
    0.09
    484
    +0.09
    0.08
    Negative Logits
     Citation
    -0.86
    ACP
    -0.85
    Enlarge
    -0.82
    :[
    -0.80
    lihood
    -0.79
     Pwr
    -0.79
    ĵĺ
    -0.79
    wana
    -0.75
     âĨij
    -0.75
     Respond
    -0.74
    POSITIVE LOGITS
     mayhem
    1.10
     assorted
    1.01
     fuss
    1.01
     frantic
    1.00
     craz
    1.00
     goofy
    1.00
     gigg
    1.00
     gossip
    0.98
     nightmares
    0.96
     angst
    0.95
    Activations Density 0.842%

    No Known Activations