© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8309
    Prev
    Next
    INDEX
    Explanations

    definitions or descriptions of various subjects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "definition."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.78
    hop
    -0.70
    umph
    -0.65
    meet
    -0.65
     Tours
    -0.64
     batches
    -0.62
    hm
    -0.62
    icket
    -0.61
    leased
    -0.61
    icip
    -0.60
    POSITIVE LOGITS
     definition
    3.89
     definitions
    2.50
     Definition
    2.44
    definition
    2.35
    Definition
    2.14
     Definitions
    1.49
     dictionary
    1.45
     description
    1.40
     define
    1.40
     defines
    1.39
    Activations Density 0.007%

    No Known Activations