© 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. 11-RES-JB
    11. 21535
    Prev
    Next
    INDEX
    Explanations

    phrases related to protests and activism against various social or political issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social protests and opposition against authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.83
    iability
    -0.80
    uckle
    -0.73
    ////////////////////////////////
    -0.70
     partName
    -0.68
    ãĥĦ
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
     fide
    -0.67
    catentry
    -0.67
     sidx
    -0.66
    POSITIVE LOGITS
     injust
    1.12
     injustice
    1.12
     austerity
    1.06
     discrimination
    0.95
     unjust
    0.94
     eviction
    0.93
     oppression
    0.93
    usterity
    0.92
     discriminatory
    0.86
     censorship
    0.86
    Activations Density 0.307%

    No Known Activations