© 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. 6-RES-JB
    11. 14483
    Prev
    Next
    INDEX
    Explanations

    phrases related to military conflicts and geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    instances of direct speech or quotes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whitney
    -0.75
     Everett
    -0.72
     Cary
    -0.72
     Darrell
    -0.70
     Edison
    -0.70
    Madison
    -0.70
     PHI
    -0.69
    Todd
    -0.69
     Courtney
    -0.68
     FTC
    -0.68
    POSITIVE LOGITS
     ceasefire
    1.06
     Nato
    1.03
     Rohingya
    1.03
    zbollah
    1.02
     PKK
    1.01
     Ankara
    1.00
     Kurdish
    0.97
     Daesh
    0.96
     YPG
    0.96
     Islamist
    0.95
    Activations Density 2.443%

    No Known Activations