© 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. 11-RES-JB
    11. 7600
    Prev
    Next
    INDEX
    Explanations

    instances of the word "policy" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to policy-related issues and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stain
    -0.76
    Ñĭ
    -0.76
    ingly
    -0.70
    batch
    -0.67
     Cruise
    -0.67
    DAY
    -0.66
    iculture
    -0.66
    apy
    -0.65
    orf
    -0.65
    ibles
    -0.64
    POSITIVE LOGITS
    making
    1.24
     makers
    1.19
    maker
    1.10
    makers
    1.10
     prescriptions
    1.06
    holders
    1.02
     stances
    0.97
    holder
    0.95
     choices
    0.92
     advisor
    0.91
    Activations Density 0.051%

    No Known Activations