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. 10-RES-JB
    6. 8763
    Prev
    Next
    INDEX
    Explanations

    terms related to a wide range of diverse options or possibilities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prints
    -0.61
    heed
    -0.56
     Ern
    -0.56
    abad
    -0.56
     tyr
    -0.55
    sie
    -0.55
    verty
    -0.55
    agate
    -0.55
    odore
    -0.54
     Yamato
    -0.53
    POSITIVE LOGITS
     of
    1.01
     thereof
    0.87
    istries
    0.76
     assortment
    0.76
     ranging
    0.75
    icult
    0.72
     Of
    0.72
     kinds
    0.71
     OF
    0.69
     incarn
    0.67
    Activations Density 0.031%

    No Known Activations