© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18058
    Prev
    Next
    INDEX
    Explanations

    teaching-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of teaching and teaching-related concepts, particularly involving kids and education

    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
    ãĥ¤
    -0.67
    iture
    -0.67
     opp
    -0.65
    elight
    -0.64
    bum
    -0.63
    NetMessage
    -0.61
    ãĤ»
    -0.60
    joy
    -0.60
    endez
    -0.60
     Ports
    -0.59
    POSITIVE LOGITS
     skills
    1.04
     lesson
    1.03
     curriculum
    0.97
     lessons
    0.95
     literacy
    0.94
     curric
    0.93
     Teach
    0.90
     fundamentals
    0.89
     humility
    0.87
     basics
    0.83
    Activations Density 0.278%

    No Known Activations