© 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. 8-RES-JB
    11. 1213
    Prev
    Next
    INDEX
    Explanations

    mentions of different governmental bodies and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific governments or political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.65
    Aug
    -0.61
    utterstock
    -0.59
    ãĤ´ãĥ³
    -0.58
    odox
    -0.56
     Trafford
    -0.56
    ãĤ¨ãĥ«
    -0.56
    BUT
    -0.54
    Ay
    -0.54
    Sept
    -0.54
    POSITIVE LOGITS
     cannot
    1.17
     understands
    1.15
     hereby
    1.04
     recognizes
    1.02
     knows
    0.99
    %"
    0.97
     deserves
    0.97
     shouldn
    0.95
     respects
    0.93
     strives
    0.93
    Activations Density 0.464%

    No Known Activations