© 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. 1-RES-JB
    11. 22217
    Prev
    Next
    INDEX
    Explanations

    specific terms or acronyms related to government, legislation, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "TR" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esville
    -0.74
    eers
    -0.71
    manship
    -0.70
    holder
    -0.70
     actionGroup
    -0.68
    ea
    -0.65
    lace
    -0.65
    hold
    -0.64
     Canary
    -0.64
     Spice
    -0.61
    POSITIVE LOGITS
    aband
    0.91
    ACK
    0.88
    acement
    0.88
    andom
    0.86
    ickle
    0.86
    RIPT
    0.86
    TR
    0.85
    ANS
    0.85
    acing
    0.83
    AN
    0.83
    Activations Density 0.004%

    No Known Activations