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. 12-RES-JB
    6. 6956
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues, such as protests, commuters, pilgrims, Christians, and doctors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to social and political groups or dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ggles
    -0.71
     ACTIONS
    -0.66
     VIDEOS
    -0.63
     Tribal
    -0.61
     External
    -0.60
    Official
    -0.60
     relevance
    -0.60
     domain
    -0.59
     Honour
    -0.58
    uras
    -0.58
    POSITIVE LOGITS
     suing
    1.00
     protesting
    1.00
     scrambling
    1.00
     stranded
    0.99
     trapped
    0.97
     looting
    0.97
     battling
    0.96
     marching
    0.95
     lining
    0.93
     fleeing
    0.90
    Activations Density 0.307%

    No Known Activations