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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9921
    Prev
    Next
    INDEX
    Explanations

    descriptions of family-friendly events or attractions

    oai_token-act-pair · gpt-3.5-turbo

    components related to family-friendly activities and dining options

    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
     Transcript
    -0.73
    usercontent
    -0.70
    cens
    -0.67
    Profile
    -0.67
    Abstract
    -0.67
    Filename
    -0.66
    )=(
    -0.65
    Reply
    -0.65
     Username
    -0.64
    failed
    -0.64
    POSITIVE LOGITS
     booths
    1.47
     lounge
    1.33
     dining
    1.32
     seating
    1.31
     festivities
    1.30
     gatherings
    1.28
     dinners
    1.27
     cafes
    1.26
     festivals
    1.26
     venues
    1.26
    Activations Density 0.399%

    No Known Activations