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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19807
    Prev
    Next
    INDEX
    Explanations

    abbreviations commonly representing places or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "UP."

    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
    ici
    -0.70
     Jordan
    -0.65
    ãĥ©
    -0.64
     Stark
    -0.62
     judgment
    -0.62
    icial
    -0.61
     judgement
    -0.61
     judgments
    -0.60
     deserts
    -0.60
     Jud
    -0.59
    POSITIVE LOGITS
    UP
    4.31
     UP
    1.98
    up
    1.94
    ups
    1.77
    Up
    1.60
    DOWN
    1.50
    UV
    1.40
    OUT
    1.37
    UC
    1.34
    FU
    1.27
    Activations Density 0.006%

    No Known Activations