© 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. 3-RES-JB
    11. 12351
    Prev
    Next
    INDEX
    Explanations

    references to educational courses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of academic courses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wrench
    -0.66
     stake
    -0.63
    usalem
    -0.63
     stranger
    -0.61
     territ
    -0.61
    York
    -0.59
    itiveness
    -0.59
     curtain
    -0.58
     colonies
    -0.57
    axy
    -0.57
    POSITIVE LOGITS
    Course
    1.30
    course
    1.17
     courses
    1.13
     Course
    1.09
     COUR
    0.99
    ourses
    0.98
     instructors
    0.96
     course
    0.90
     instructor
    0.83
    renheit
    0.81
    Activations Density 0.023%

    No Known Activations