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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3571
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions and investigations in contexts like police reports, official statements, and emergency declarations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of criminal conduct and legal investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     obscure
    -0.79
     piled
    -0.77
     camoufl
    -0.75
     leap
    -0.73
     pigeon
    -0.73
     enchanted
    -0.72
     whiff
    -0.72
     invent
    -0.72
     fancy
    -0.71
     morp
    -0.71
    POSITIVE LOGITS
    Thank
    1.27
    Statement
    1.15
    Our
    1.15
    ï¸ı
    1.13
     Thank
    1.11
    We
    1.07
    âĢ
    1.01
    Please
    0.99
    ###
    0.97
    âĢİ
    0.97
    Activations Density 0.416%

    No Known Activations