© 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. 11-RES-JB
    6. 1774
    Prev
    Next
    INDEX
    Explanations

    phrases related to having something, specifically the phrase "on [something]" where the "something" refers to a physical location or possession

    oai_token-act-pair · gpt-3.5-turbo

    the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \-
    -0.68
    mini
    -0.67
    orically
    -0.67
    ano
    -0.65
    ricanes
    -0.64
    asy
    -0.62
     practicable
    -0.62
    Ī
    -0.62
     IPM
    -0.61
    ¯
    -0.61
    POSITIVE LOGITS
     display
    1.28
     offer
    1.26
     hand
    1.07
    erous
    1.06
     sale
    1.04
     board
    1.03
    site
    1.03
     standby
    1.00
    screen
    0.99
    deck
    0.89
    Activations Density 0.136%

    No Known Activations