© 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. 18089
    Prev
    Next
    INDEX
    Explanations

    names or words related to celebrities or high-profile figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "catch" or its variations

    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
     Fas
    -0.67
     stren
    -0.66
     perpet
    -0.64
     ref
    -0.61
     prost
    -0.61
     plaque
    -0.60
     Voc
    -0.60
     Wikipedia
    -0.59
     origins
    -0.59
     moder
    -0.59
    POSITIVE LOGITS
    atch
    4.72
    atches
    2.48
    atching
    2.32
    ATCH
    2.18
    atched
    2.12
    atcher
    1.43
    atche
    1.19
    itch
    1.13
    essage
    1.11
    ount
    0.99
    Activations Density 0.017%

    No Known Activations