© 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
    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. 24411
    Prev
    Next
    INDEX
    Explanations

    information regarding event details such as ticket prices, age restrictions, and admission rules

    oai_token-act-pair · gpt-3.5-turbo

    information related to ticket pricing and admission details

    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
    âĹ¼
    -1.12
    inventoryQuantity
    -0.75
     subp
    -0.72
    TPPStreamerBot
    -0.70
    itative
    -0.69
    Ò
    -0.68
    yang
    -0.68
     billions
    -0.67
    Ó
    -0.66
     unconsciously
    -0.65
    POSITIVE LOGITS
     admission
    1.19
     Admission
    1.17
     seating
    1.13
     Guests
    1.11
     Adults
    1.11
     reservations
    1.09
     attendees
    1.08
     VIP
    1.04
     complimentary
    1.03
     reservation
    1.02
    Activations Density 0.388%

    No Known Activations