© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7106
    Prev
    Next
    INDEX
    Explanations

    classrooms or educational settings

    oai_token-act-pair · gpt-3.5-turbo

    references to educational classes and courses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axy
    -0.80
    iciary
    -0.70
    vernment
    -0.63
    alty
    -0.63
     Chains
    -0.61
    riot
    -0.60
    rification
    -0.60
     cyn
    -0.60
    agate
    -0.59
    \":
    -0.59
    POSITIVE LOGITS
     taught
    1.44
     curriculum
    1.27
     curric
    1.18
     instructors
    1.16
     syll
    1.16
     instructor
    1.12
     teaches
    1.09
     teach
    1.04
     courses
    1.04
     Instructor
    1.02
    Activations Density 0.099%

    No Known Activations