© 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. 19294
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and government entities

    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
    onym
    -0.77
    alyses
    -0.67
    ourced
    -0.65
    eatured
    -0.61
     coded
    -0.59
     simulated
    -0.58
     refere
    -0.58
     redacted
    -0.57
     died
    -0.56
     Consent
    -0.56
    POSITIVE LOGITS
     brass
    0.85
     faithful
    0.85
     fans
    0.84
     considering
    0.82
     amid
    0.82
     prospects
    0.81
    seekers
    0.79
    é¾įåĸļ士
    0.79
     enthusi
    0.77
     supporters
    0.76
    Activations Density 0.375%

    No Known Activations