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. 8-RES-JB
    6. 21204
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events

    oai_token-act-pair · gpt-3.5-turbo

    statements related to casualties and conflict situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Briggs
    -0.80
     Edison
    -0.76
     Everett
    -0.72
     Vaughn
    -0.72
     Courtney
    -0.72
     Darrell
    -0.70
     dime
    -0.69
     Robbins
    -0.68
     Madison
    -0.68
     Buddy
    -0.68
    POSITIVE LOGITS
    zbollah
    1.15
     Rohingya
    1.11
     Kurdish
    1.04
     Hezbollah
    1.04
     ceasefire
    1.03
    ÄŁ
    1.03
     Islamist
    1.02
    Syria
    1.02
     Houth
    1.01
     PKK
    1.01
    Activations Density 2.283%

    No Known Activations