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

    Neuronpedia

    Jacobian LensNEW
    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. 14871
    Prev
    Next
    INDEX
    Explanations

    information related to people's professional backgrounds and roles in various government, law enforcement, and media organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to political or professional roles and careers

    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
    photos
    -0.78
    yout
    -0.68
     Fans
    -0.67
     strangers
    -0.66
    Christmas
    -0.66
    wake
    -0.63
     senseless
    -0.63
    malink
    -0.61
    otrop
    -0.61
     Songs
    -0.60
    POSITIVE LOGITS
     stint
    1.27
     cler
    1.09
     overseeing
    1.02
     oversaw
    1.00
     advising
    1.00
     administrations
    0.96
     positions
    0.93
     chaired
    0.92
     tenure
    0.91
     serving
    0.91
    Activations Density 0.270%

    No Known Activations