© 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. 10-RES-JB
    11. 2721
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    themes related to political power dynamics and societal issues

    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
    Daddy
    -0.74
    agate
    -0.65
    antine
    -0.65
    ibal
    -0.65
    sterdam
    -0.64
    prints
    -0.64
    inventoryQuantity
    -0.62
    orb
    -0.62
    tein
    -0.61
     Hitchcock
    -0.61
    POSITIVE LOGITS
     population
    1.51
     populace
    1.50
     populations
    1.45
     citizens
    1.37
     electorate
    1.34
     minorities
    1.30
     masses
    1.29
     oppressed
    1.22
     voters
    1.20
     citizen
    1.13
    Activations Density 0.644%

    No Known Activations