© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 18557
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and statements

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about political situations or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosby
    -0.74
     bleach
    -0.74
     Craigslist
    -0.72
     Bigfoot
    -0.71
     Gotham
    -0.70
     seams
    -0.69
     sucker
    -0.69
     Yosemite
    -0.69
     Manson
    -0.68
     blight
    -0.68
    POSITIVE LOGITS
     Lavrov
    1.20
     Azerbai
    1.14
     diplomatic
    1.07
     delegation
    1.02
     consultations
    1.01
    ÄŁ
    1.00
     Rouhani
    1.00
     envoy
    0.98
     bilateral
    0.97
    ÅŁ
    0.97
    Activations Density 1.025%

    No Known Activations