© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12844
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocacy and unity, specifically in a call for collective action or support

    oai_token-act-pair · gpt-3.5-turbo

    calls to action for collective support and solidarity

    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
    Ö¼
    -0.76
    neau
    -0.76
    ©¶æ¥µ
    -0.74
     spa
    -0.72
    Course
    -0.72
     psychiatrist
    -0.72
     hindsight
    -0.72
     neglig
    -0.72
    illac
    -0.70
     inexper
    -0.69
    POSITIVE LOGITS
     solidarity
    1.31
     protest
    1.30
     Protest
    1.24
     petition
    1.11
     petitions
    1.10
     boycott
    1.10
     protesting
    1.09
     Against
    1.06
    Against
    1.03
    against
    1.02
    Activations Density 1.041%

    No Known Activations