© 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. 4543
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and opinions

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

    assertions and arguments in a political context

    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
     exting
    -0.79
    Reviewed
    -0.78
     pione
    -0.77
    ā
    -0.76
    Đ
    -0.76
    û
    -0.76
    Ď
    -0.76
    č
    -0.76
    ċ
    -0.76
    ă
    -0.75
    POSITIVE LOGITS
     secondly
    0.97
     obviously
    0.92
     yeah
    0.92
     ultimately
    0.88
     frankly
    0.87
     unfortunately
    0.84
     everybody
    0.84
     we
    0.82
     sometimes
    0.82
     fortunately
    0.81
    Activations Density 0.367%

    No Known Activations