© 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. 1-RES-JB
    11. 20282
    Prev
    Next
    INDEX
    Explanations

    product or inventory-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of items, specifically in the context of trading or selling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Durham
    -0.71
    govern
    -0.67
     Rider
    -0.66
    BILITY
    -0.66
     Telegram
    -0.65
    orks
    -0.65
     DH
    -0.64
     2022
    -0.64
     Vide
    -0.64
     Channel
    -0.63
    POSITIVE LOGITS
     items
    1.34
    items
    1.13
     Items
    1.01
    Items
    1.01
     belongings
    0.99
     item
    0.98
    item
    0.98
    abilia
    0.93
    mith
    0.89
    EMS
    0.89
    Activations Density 0.014%

    No Known Activations