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. 16669
    Prev
    Next
    INDEX
    Explanations

    short phrases starting with "Part of" followed by a description

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "part of" followed by various nouns and concepts

    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
     butcher
    -0.70
     slightest
    -0.66
     cyt
    -0.65
    reys
    -0.64
    Champ
    -0.63
    dayName
    -0.62
    ENCE
    -0.62
    gins
    -0.61
     spiders
    -0.61
     DRAG
    -0.60
    POSITIVE LOGITS
    assing
    0.65
     Armored
    0.64
     Hess
    0.62
     Kessler
    0.61
    thouse
    0.61
    milo
    0.61
    assed
    0.61
    scription
    0.60
     GDP
    0.60
     Shutdown
    0.59
    Activations Density 0.087%

    No Known Activations