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. 11-RES-JB
    6. 22844
    Prev
    Next
    INDEX
    Explanations

    technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "article."

    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
     Sleeping
    -0.68
     Governors
    -0.66
    etheless
    -0.66
    Lens
    -0.65
    Tokens
    -0.62
    selves
    -0.59
     Lac
    -0.58
    ICE
    -0.57
     Kinnikuman
    -0.56
    SSL
    -0.56
    POSITIVE LOGITS
     assumes
    1.24
     contains
    1.20
     summarizes
    1.12
     examines
    1.11
     discusses
    1.07
     focuses
    1.06
     describes
    1.05
     applies
    1.04
     explores
    1.03
     intends
    1.03
    Activations Density 0.094%

    No Known Activations