© 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. 0-RES-JB
    11. 440
    Prev
    Next
    INDEX
    Explanations

    instances of the word "institute."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of establishment or creation of entities, organizations, or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sparrow
    -0.71
     Played
    -0.70
     Tact
    -0.69
    raw
    -0.69
     Pitch
    -0.66
     Thumbnails
    -0.65
     Memories
    -0.65
     Warrant
    -0.65
    Beaut
    -0.63
     Vinyl
    -0.62
    POSITIVE LOGITS
     institute
    3.63
     instit
    2.59
     instituted
    1.58
     institution
    1.33
     Instit
    1.14
     appoint
    1.14
     levy
    1.12
     implement
    1.06
     Institute
    1.03
     abolish
    1.00
    Activations Density 0.020%

    No Known Activations