© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    keywords related to political, governmental, and analytical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to people or groups involved in political or analytical discussions

    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
     instantaneous
    -0.72
     10000
    -0.63
     Elias
    -0.62
     1440
    -0.61
     Permanent
    -0.61
     8000
    -0.61
    York
    -0.61
     Rutherford
    -0.59
     Then
    -0.59
     permanent
    -0.59
    POSITIVE LOGITS
     unfairly
    1.49
     underestimated
    1.33
     lacked
    1.31
     misunderstand
    1.29
     overest
    1.28
     underestimate
    1.26
     underest
    1.23
     misunderstood
    1.23
     misrepresent
    1.22
     inadequ
    1.19
    Activations Density 0.357%

    No Known Activations