© 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. 29645
    Prev
    Next
    INDEX
    Explanations

    references to job titles and formal positions

    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
    373
    +0.14
    0.7%
    349
    +0.13
    0.6%
    514
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.14
    0.08
    584
    +0.13
    0.07
    23
    +0.11
    0.06
    Negative Logits
     mamm
    -0.87
     tuna
    -0.78
     conserv
    -0.77
     Mous
    -0.75
     FAT
    -0.73
     Whitman
    -0.73
     Leopard
    -0.73
     Tup
    -0.72
     Zin
    -0.72
    ovie
    -0.70
    POSITIVE LOGITS
    âķIJâķIJ
    2.10
    âķIJ
    1.66
    âķ
    1.25
    âĸ¬âĸ¬
    1.21
    âĸ¬
    1.17
    âĸĪâĸĪâĸĪâĸĪ
    1.04
    âĸĪâĸĪ
    1.03
    Ĺ
    0.95
    vine
    0.94
    ij
    0.90
    Activations Density 0.452%

    No Known Activations