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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 888
    Prev
    Next
    INDEX
    Explanations

    phrases related to public demonstrations and political chants

    oai_token-act-pair · gpt-3.5-turbo

    instances of chanting and slogans in a protest context

    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
    neau
    -0.76
    士
    -0.76
    folio
    -0.72
    iciary
    -0.71
    amate
    -0.69
    venture
    -0.69
    nel
    -0.68
    Released
    -0.68
    ahime
    -0.67
     Tycoon
    -0.67
    POSITIVE LOGITS
     slogans
    1.37
     chanting
    1.21
     chants
    1.20
     chanted
    1.11
     chant
    0.94
     loudly
    0.92
     aloud
    0.89
     louder
    0.87
     praises
    0.86
     goodbye
    0.84
    Activations Density 0.077%

    No Known Activations