© 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. 2438
    Prev
    Next
    INDEX
    Explanations

    words related to drinking establishments or items commonly associated with bars, such as "pint"

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of liquid containers, particularly pints, quarts, and gallons

    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
     marrow
    -0.76
    HI
    -0.72
    DER
    -0.69
    termination
    -0.67
    SOURCE
    -0.66
    iders
    -0.66
    byss
    -0.65
    olves
    -0.65
    bers
    -0.64
    phe
    -0.64
    POSITIVE LOGITS
     jars
    0.93
     gallon
    0.93
     pint
    0.89
    ature
    0.87
     jar
    0.86
     flask
    0.83
    pick
    0.81
     bucket
    0.77
    alore
    0.76
    asks
    0.75
    Activations Density 0.014%

    No Known Activations