© 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. 8-RES-JB
    11. 6334
    Prev
    Next
    INDEX
    Explanations

    legislation-related keywords and phrases

    oai_token-act-pair · gpt-3.5-turbo

    government-related terms and phrases indicating the creation, retention, or alteration of laws and regulations

    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
     Passion
    -0.89
    angelo
    -0.74
     Mub
    -0.64
     Osiris
    -0.64
     Atmosp
    -0.62
     infinity
    -0.61
    pring
    -0.60
     microsc
    -0.59
     psyche
    -0.59
     Nile
    -0.58
    POSITIVE LOGITS
     protections
    1.00
    osponsors
    0.93
     federally
    0.88
     decriminal
    0.87
     loopholes
    0.82
     repealed
    0.82
     amnesty
    0.81
     exemptions
    0.80
    untary
    0.80
     unconstitutional
    0.79
    Activations Density 0.329%

    No Known Activations