© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 17388
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politicians

    oai_token-act-pair · gpt-3.5-turbo

    the names and affiliations of political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ript
    -0.77
    stellar
    -0.74
     Tests
    -0.67
     Serpent
    -0.67
    orp
    -0.66
     Corsair
    -0.66
     Gladiator
    -0.64
     Viking
    -0.64
     Phant
    -0.63
     decomp
    -0.63
    POSITIVE LOGITS
     appoint
    1.00
     Nieto
    0.87
     Lyndon
    0.87
     reelection
    0.86
     Caucus
    0.84
    Senate
    0.83
     Appropriations
    0.82
     Feinstein
    0.82
    itol
    0.81
    Republicans
    0.79
    Activations Density 0.491%

    No Known Activations