© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3698
    Prev
    Next
    INDEX
    Explanations

    technical terms or phrases related to policies and political actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to political dynamics and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ÃĥÃĤ
    -0.80
    icol
    -0.74
    Þ
    -0.73
    ñ
    -0.70
    %:
    -0.70
    oppable
    -0.69
    krit
    -0.68
     pione
    -0.67
    ooters
    -0.65
    ãĤ¡
    -0.65
    POSITIVE LOGITS
     to
    1.52
     thereto
    1.06
    to
    1.00
     TO
    0.85
     To
    0.78
    To
    0.78
     unto
    0.78
     toward
    0.70
     towards
    0.68
     ta
    0.68
    Activations Density 1.112%

    No Known Activations