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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 2469
    Prev
    Next
    INDEX
    Explanations

    solutions to various kinds of problems

    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
    idth
    -0.80
    yip
    -0.70
    ramid
    -0.69
    rium
    -0.69
    ogly
    -0.63
    letters
    -0.59
    weeney
    -0.58
    gow
    -0.58
    rongh
    -0.57
    attering
    -0.56
    POSITIVE LOGITS
     satisf
    1.21
     peacefully
    1.04
     administr
    1.03
     surg
    0.96
     promptly
    0.94
     by
    0.93
     diplom
    0.91
     via
    0.90
     swiftly
    0.87
     manually
    0.85
    Activations Density 0.173%

    No Known Activations