© 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. 11-RES-JB
    11. 11125
    Prev
    Next
    INDEX
    Explanations

    keywords related to various organizations, such as Drug Analysis, Crime Prevention, and Environmental Sciences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drugs and their analysis, as well as various social issues and enforcement activities

    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
     castles
    -0.84
     canoe
    -0.82
     gigs
    -0.82
     chords
    -0.81
     mushrooms
    -0.77
     quartz
    -0.77
     eclipse
    -0.76
     stacked
    -0.76
     stars
    -0.75
     bargain
    -0.75
    POSITIVE LOGITS
     Protection
    1.48
     Abuse
    1.46
     Enforcement
    1.40
     Identification
    1.38
     Monitoring
    1.38
     Assessment
    1.38
     Reduction
    1.37
     Prevention
    1.37
     Safety
    1.37
     Management
    1.36
    Activations Density 0.232%

    No Known Activations