© 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. 11-RES-JB
    11. 13672
    Prev
    Next
    INDEX
    Explanations

    specific government agencies and organizations in requests or calls to action for official actions or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to government agencies and departments

    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
    icka
    -0.70
    ilings
    -0.60
     prest
    -0.58
    ilogy
    -0.57
    ¥µ
    -0.54
    alach
    -0.53
    favorite
    -0.53
    izoph
    -0.52
    iping
    -0.52
    Ranked
    -0.52
    POSITIVE LOGITS
     to
    1.07
    to
    0.73
     not
    0.71
     intervene
    0.70
     reconsider
    0.70
     urgently
    0.70
     permission
    0.67
     rethink
    0.64
    erity
    0.62
     TO
    0.61
    Activations Density 0.145%

    No Known Activations