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. 1-RES-JB
    6. 16699
    Prev
    Next
    INDEX
    Explanations

    information about specific topics or entities as described in the "\|endoftext\|" sections

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "About."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.72
    itely
    -0.69
    itiz
    -0.66
    oly
    -0.65
    rift
    -0.65
    alian
    -0.64
    eful
    -0.62
     cage
    -0.62
    efully
    -0.62
     tast
    -0.62
    POSITIVE LOGITS
    About
    0.94
     Citation
    0.74
     Us
    0.73
    ahime
    0.71
    Submit
    0.70
     Consent
    0.70
     Seym
    0.69
     WATCHED
    0.68
    doms
    0.68
     demographics
    0.67
    Activations Density 0.023%

    No Known Activations