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. 17774
    Prev
    Next
    INDEX
    Explanations

    closures or conclusions in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "CLOSE"

    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
    etheless
    -0.95
     challeng
    -0.88
    foreseen
    -0.86
     surpr
    -0.86
     comprom
    -0.81
     tremend
    -0.80
    informed
    -0.80
     offsets
    -0.79
     skelet
    -0.78
     pse
    -0.78
    POSITIVE LOGITS
     Hundreds
    1.11
     Protesters
    1.10
     Officials
    1.09
     Former
    1.08
     Highlights
    1.06
     Thousands
    1.05
     Dozens
    1.02
     Scenes
    1.00
     Researchers
    1.00
     Actress
    0.99
    Activations Density 0.040%

    No Known Activations