© 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. 0-RES-JB
    11. 11989
    Prev
    Next
    INDEX
    Explanations

    names containing the phrase "Ri" at the end

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific regulatory or legal entity

    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
     concealed
    -0.70
     bob
    -0.70
     chrome
    -0.68
     whales
    -0.67
     airs
    -0.66
     requisite
    -0.66
     ether
    -0.64
     accidental
    -0.64
     subscribed
    -0.63
     air
    -0.63
    POSITIVE LOGITS
    RI
    4.31
    RY
    1.70
    ri
    1.67
    RIC
    1.49
     RI
    1.49
    MI
    1.43
    RA
    1.37
    RO
    1.37
    RE
    1.30
    rie
    1.25
    Activations Density 0.011%

    No Known Activations