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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 11629
    Prev
    Next
    INDEX
    Explanations

    resources such as tutorials, books, articles, and speeches on various topics

    oai_token-act-pair · gpt-3.5-turbo

    references to various media and information sources

    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
    erity
    -0.89
    radius
    -0.81
    SIZE
    -0.80
    eland
    -0.78
    ãĥĺãĥ©
    -0.77
    ãĤ¨ãĥ«
    -0.77
    Shape
    -0.75
    ãĥ«
    -0.75
    Size
    -0.74
    width
    -0.72
    POSITIVE LOGITS
     seminars
    1.43
     conferences
    1.38
     interviews
    1.31
     presentations
    1.28
     dinners
    1.26
     invitations
    1.26
     briefings
    1.25
     announcements
    1.22
     endorsements
    1.22
     newsletters
    1.20
    Activations Density 0.493%

    No Known Activations