© 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. 10-RES-JB
    11. 11223
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to educational institutions, specifically "school"

    oai_token-act-pair · gpt-3.5-turbo
    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
     GOODMAN
    -0.69
     disapp
    -0.67
     goodbye
    -0.65
     rainy
    -0.60
     Dying
    -0.60
     underwater
    -0.59
     bluff
    -0.59
     ABE
    -0.57
     slee
    -0.56
     innocence
    -0.56
    POSITIVE LOGITS
    itzer
    0.91
    artz
    0.89
    uble
    0.89
    enberg
    0.87
    acher
    0.86
    lein
    0.85
    berg
    0.82
    berger
    0.80
    feld
    0.80
    ulkan
    0.79
    Activations Density 0.030%

    No Known Activations