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. 12156
    Prev
    Next
    INDEX
    Explanations

    references to a specific word or character sequence, "Ro zz"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Ro z z" and variations of it

    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
     Polar
    -0.71
     lapse
    -0.68
    vict
    -0.68
     Conrad
    -0.68
     foremost
    -0.67
     Scots
    -0.67
     fitness
    -0.66
     appropriation
    -0.65
     conditioning
    -0.64
    ¥µ
    -0.62
    POSITIVE LOGITS
    zz
    1.23
    arella
    1.12
    ucc
    0.97
    ZZ
    0.95
    arro
    0.95
    olla
    0.94
    hou
    0.93
    Feed
    0.92
    azz
    0.90
    edd
    0.90
    Activations Density 0.017%

    No Known Activations