© 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. 6415
    Prev
    Next
    INDEX
    Explanations

    economic terms related to goods and services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to commodities and services

    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
    thia
    -0.64
    early
    -0.64
    adian
    -0.63
    noon
    -0.63
    herty
    -0.63
    ANC
    -0.62
    ANCE
    -0.62
    aeper
    -0.62
    inct
    -0.62
    REAM
    -0.61
    POSITIVE LOGITS
     shipped
    1.05
     manufactured
    1.04
     sold
    1.04
     marketed
    1.02
     goods
    1.02
     imports
    0.99
    stuff
    0.97
     produced
    0.96
     priced
    0.96
     exports
    0.95
    Activations Density 0.111%

    No Known Activations