Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16891
    Prev
    Next
    INDEX
    Explanations

    a specific pattern in the text, specifically the abbreviation "UP" followed by a number, potentially related to locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "UP" indicating the University Press or related institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resonance
    -0.65
     enclosed
    -0.65
    croft
    -0.62
    wagen
    -0.60
    rosso
    -0.60
    paio
    -0.59
    azer
    -0.58
    avia
    -0.58
     Camel
    -0.58
     Murdoch
    -0.58
    POSITIVE LOGITS
    PER
    1.22
    olicy
    1.09
    PDATE
    1.07
    ERT
    1.04
    ERN
    0.95
    IED
    0.94
    FER
    0.93
    PLIC
    0.93
    rompt
    0.91
    LOAD
    0.91
    Activations Density 0.011%

    No Known Activations