© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18739
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and activism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social movements and activism, particularly focusing on liberation and striving for equality

    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
    odium
    -0.65
    gran
    -0.65
    ðŁĺ
    -0.64
     Daylight
    -0.63
     expired
    -0.61
     Chaff
    -0.58
     Photos
    -0.58
     Weekend
    -0.56
    });
    -0.56
     Emails
    -0.56
    POSITIVE LOGITS
     solely
    0.99
     consciously
    0.99
     chiefly
    0.98
     principally
    0.95
     fundamentally
    0.94
     instinctively
    0.94
     strictly
    0.94
     primarily
    0.93
     relentlessly
    0.90
     squarely
    0.89
    Activations Density 0.368%

    No Known Activations