© 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. 3-RES-JB
    11. 15655
    Prev
    Next
    INDEX
    Explanations

    acronyms related to locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "UP," which likely stands for "Uttar Pradesh" or another context-specific term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auga
    -0.64
    ãĥĸ
    -0.64
     Germans
    -0.62
     Murdoch
    -0.62
    ¯¯¯¯
    -0.62
    piece
    -0.62
     enclosed
    -0.61
    ãĥĪ
    -0.61
    paio
    -0.60
    jah
    -0.60
    POSITIVE LOGITS
    PER
    1.18
    PDATE
    1.17
    olicy
    1.17
    ON
    1.02
    CHAT
    1.02
    UP
    1.01
    stairs
    1.01
    IED
    1.01
    FER
    0.97
    rompt
    0.96
    Activations Density 0.006%

    No Known Activations