Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8786
    Prev
    Next
    INDEX
    Explanations

    references to institutions and official bodies such as the United Nations

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Nations and its various bodies and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Klopp
    -0.81
    paio
    -0.75
    veland
    -0.74
    osaurus
    -0.74
     Canter
    -0.73
     Gillespie
    -0.70
    hattan
    -0.69
     Dane
    -0.68
     Arpaio
    -0.67
     NJ
    -0.65
    POSITIVE LOGITS
     Security
    1.21
     Framework
    1.09
     envoy
    1.00
     Refugee
    0.95
     humanitarian
    0.95
     Assistance
    0.94
     Ambassador
    0.93
     Convention
    0.93
     Relief
    0.90
     Declaration
    0.90
    Activations Density 0.068%

    No Known Activations