© 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. 0-RES-JB
    11. 20234
    Prev
    Next
    INDEX
    Explanations

    the terms "independent" and "dependent," with a slightly higher activation for "independent."

    oai_token-act-pair · gpt-3.5-turbo

    references to political or organizational affiliations, particularly "independent" and "Labour."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pack
    -0.75
     heroes
    -0.73
     Cass
    -0.73
     checklist
    -0.72
     paraph
    -0.72
     Bans
    -0.72
     backlog
    -0.71
     Pack
    -0.71
     extrap
    -0.68
     dread
    -0.68
    POSITIVE LOGITS
    independent
    2.97
    independence
    1.83
    dependent
    1.82
    Labour
    1.66
    Independent
    1.61
    estate
    1.56
    uve
    1.33
    democracy
    1.23
    condition
    1.18
    castle
    1.18
    Activations Density 0.050%

    No Known Activations