© 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. 11-RES-JB
    11. 22659
    Prev
    Next
    INDEX
    Explanations

    various political and ideological terms, particularly related to parties, movements, and historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties and ideologies

    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
    ModLoader
    -0.79
    worthy
    -0.76
    idious
    -0.71
    Rated
    -0.64
    pmwiki
    -0.64
    cedented
    -0.63
    ful
    -0.62
    é¾įå¥ij士
    -0.62
    yss
    -0.62
    acious
    -0.61
    POSITIVE LOGITS
    doms
    0.87
    ties
    0.80
     groups
    0.80
     movement
    0.78
     NETWORK
    0.78
     group
    0.77
    iaries
    0.76
     organization
    0.76
     enclave
    0.76
     organizations
    0.75
    Activations Density 0.323%

    No Known Activations