© 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. 10-RES_POST_32K-OAI
    11. 29720
    Prev
    Next
    INDEX
    Explanations

    terms related to confusion or disruption in actions and experiences

    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
    277
    +0.13
    0.6%
    70
    +0.10
    0.5%
    48
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.13
    0.06
    351
    +0.10
    0.04
    271
    +0.10
    0.04
    Negative Logits
    vation
    -0.98
     Citation
    -0.76
    Interstitial
    -0.75
    ãĥ´
    -0.71
     Cosponsors
    -0.69
    iva
    -0.67
    uti
    -0.63
    icipated
    -0.62
    rica
    -0.62
    eele
    -0.60
    POSITIVE LOGITS
     around
    1.40
    around
    1.27
     Around
    1.15
    Around
    1.02
     havoc
    1.01
     away
    0.76
     things
    0.74
     round
    0.72
    ily
    0.69
     Away
    0.67
    Activations Density 0.389%

    No Known Activations