© 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. 10-RES-JB
    11. 11276
    Prev
    Next
    INDEX
    Explanations

    words associated with political ideologies and terms related to definitions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lie" or variations of it, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.81
     Axel
    -0.79
     Polk
    -0.76
     bun
    -0.75
     reflex
    -0.75
     Zeit
    -0.74
     Qi
    -0.73
     SAM
    -0.73
     Slug
    -0.73
     Caleb
    -0.72
    POSITIVE LOGITS
    actual
    1.35
    outside
    1.32
    nob
    1.32
    traditional
    1.31
    other
    1.29
    every
    1.28
    nothing
    1.27
    ever
    1.26
    everything
    1.26
    there
    1.26
    Activations Density 0.146%

    No Known Activations