© 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 EvalsExportsinterp-engineNEWAPI 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. 31348
    Prev
    Next
    INDEX
    Explanations

    instances of notable events or situations, particularly involving infrastructure and public safety

    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
    657
    +0.14
    0.6%
    238
    +0.11
    0.5%
    379
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    753
    +0.14
    0.06
    249
    +0.11
    0.05
    152
    +0.11
    0.09
    Negative Logits
     seiz
    -0.84
     roomm
    -0.73
     mates
    -0.72
    osponsors
    -0.70
    Parents
    -0.68
    mates
    -0.67
     interns
    -0.67
     cand
    -0.66
     Monstrous
    -0.65
     Pupp
    -0.65
    POSITIVE LOGITS
     highways
    1.48
     artery
    1.47
     arteries
    1.47
     highway
    1.36
     bridges
    1.36
     roadway
    1.28
     freeway
    1.26
     rail
    1.25
     tunnels
    1.25
     canal
    1.25
    Activations Density 2.149%

    No Known Activations