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

    Neuronpedia

    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. 11-RES-JB
    11. 7636
    Prev
    Next
    INDEX
    Explanations

    phrases related to political seats and elections

    oai_token-act-pair · gpt-3.5-turbo

    references to political positions or seats in various contexts

    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
    ICLE
    -0.74
    DragonMagazine
    -0.71
    Shock
    -0.66
     Turtles
    -0.66
     propulsion
    -0.61
     Mothers
    -0.61
    culosis
    -0.59
     msec
    -0.59
    SOURCE
    -0.59
     compulsion
    -0.59
    POSITIVE LOGITS
     vacated
    1.49
     vacant
    1.24
    holder
    1.14
    holders
    1.08
     vacancies
    0.92
    hold
    0.89
     held
    0.88
    ģ«
    0.85
     holders
    0.85
     occupied
    0.84
    Activations Density 0.096%

    No Known Activations