© 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 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. 9-RES-JB
    11. 19761
    Prev
    Next
    INDEX
    Explanations

    terms related to protest actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to protests and activism against various issues or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.84
    ãĥĥãĥī
    -0.81
    è¯
    -0.75
    ãĥ¯
    -0.75
    ãĤ§
    -0.74
    è£
    -0.73
     Crusher
    -0.72
    ãĥĦ
    -0.71
    ********************************
    -0.70
    glers
    -0.69
    POSITIVE LOGITS
     injust
    1.19
     injustice
    1.12
     oppression
    0.98
     oppressive
    0.95
    government
    0.88
     unjust
    0.86
     austerity
    0.86
     government
    0.86
     intolerance
    0.84
     violence
    0.83
    Activations Density 0.264%

    No Known Activations