© 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. 9-RES-JB
    11. 11681
    Prev
    Next
    INDEX
    Explanations

    decisions or actions related to whether to pursue legal actions or charges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decisions and considerations about prosecution or charging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Basics
    -0.71
    Lear
    -0.70
    sav
    -0.70
    Mom
    -0.68
    facts
    -0.67
     Maze
    -0.67
     Whats
    -0.66
     ignorance
    -0.66
    PsyNetMessage
    -0.66
    Weak
    -0.64
    POSITIVE LOGITS
     recommend
    1.25
     recommending
    1.21
     publish
    1.10
     pursue
    1.06
     approve
    1.04
     renew
    1.03
     endorse
    1.03
     proceed
    1.03
     accept
    1.01
     participate
    0.98
    Activations Density 0.428%

    No Known Activations