© 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. 21136
    Prev
    Next
    INDEX
    Explanations

    phrases related to course syllabus adjustments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to course structure and scheduling

    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
    advertising
    -0.81
    illard
    -0.80
     suspic
    -0.76
    soType
    -0.72
    estate
    -0.71
     sentimental
    -0.71
     greedy
    -0.71
     upset
    -0.70
     unaccount
    -0.70
    aretz
    -0.69
    POSITIVE LOGITS
     Instructor
    1.96
    Course
    1.93
     lectures
    1.82
     Course
    1.80
     instructor
    1.76
     Lect
    1.75
     courses
    1.75
     seminar
    1.69
     curriculum
    1.64
     seminars
    1.63
    Activations Density 0.484%

    No Known Activations