© 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. 9-RES-JB
    11. 11358
    Prev
    Next
    INDEX
    Explanations

    references to political figures or politically related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "political" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.74
     Warrant
    -0.72
    urat
    -0.70
     Ved
    -0.69
     pity
    -0.68
     warrants
    -0.67
     Gutenberg
    -0.66
     recall
    -0.65
     Blazing
    -0.65
     Norn
    -0.65
    POSITIVE LOGITS
    icians
    1.64
    ician
    1.51
    ifact
    1.31
    ically
    1.20
    eness
    1.16
    icial
    1.12
    ico
    1.11
    ique
    1.03
    icans
    1.02
    icking
    1.01
    Activations Density 0.036%

    No Known Activations