© 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. 0-RES-JB
    11. 7705
    Prev
    Next
    INDEX
    Explanations

    mentions of political aides

    oai_token-act-pair · gpt-3.5-turbo

    references to political aides and staffers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    views
    -0.83
    wolves
    -0.75
     brands
    -0.74
    rants
    -0.73
    umers
    -0.73
    Jews
    -0.72
     Europeans
    -0.70
    atories
    -0.70
     consumers
    -0.70
    rational
    -0.69
    POSITIVE LOGITS
     aide
    3.57
     staffer
    1.74
     adviser
    1.63
     advisor
    1.55
     aid
    1.46
     ally
    1.35
     tutor
    1.31
     aides
    1.30
     assistant
    1.28
     sergeant
    1.27
    Activations Density 0.014%

    No Known Activations