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. 11-RES-JB
    6. 18195
    Prev
    Next
    INDEX
    Explanations

    technology company names

    oai_token-act-pair · gpt-3.5-turbo

    references to brand names and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :(
    -0.62
    ":"/
    -0.59
    =\"
    -0.55
    ptive
    -0.55
     guiActiveUnfocused
    -0.55
    gression
    -0.55
     inconsist
    -0.54
    quartered
    -0.54
     aback
    -0.54
     guiActiveUn
    -0.53
    POSITIVE LOGITS
     etc
    1.66
     and
    1.35
    etc
    1.30
     &
    1.14
     et
    1.06
    and
    0.90
     AND
    0.88
     And
    0.78
     Seym
    0.73
     Moroc
    0.70
    Activations Density 0.205%

    No Known Activations