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. 9-RES-JB
    6. 15232
    Prev
    Next
    INDEX
    Explanations

    single-letter 'C' followed by the number '9' or '10'

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yamaha
    -0.64
     Tinder
    -0.64
     timeout
    -0.64
     life
    -0.60
     Lange
    -0.60
     Sov
    -0.60
     Gors
    -0.60
     advers
    -0.60
     baskets
    -0.59
     bottleneck
    -0.58
    POSITIVE LOGITS
    URRENT
    1.31
    overed
    1.29
    ategories
    1.27
    onsequ
    1.26
    rouch
    1.20
    ursed
    1.18
    ategor
    1.18
    riminal
    1.17
    onduct
    1.17
    ologne
    1.17
    Activations Density 0.062%

    No Known Activations