© 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. 8-RES-JB
    11. 7058
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic indicators and quantities

    oai_token-act-pair · gpt-3.5-turbo

    statistical measures and comparisons related to per capita data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boys
    -0.62
     Latin
    -0.62
     itch
    -0.61
     numb
    -0.60
    ogens
    -0.60
     nort
    -0.59
     moder
    -0.59
     pubs
    -0.59
     vom
    -0.59
     Wiley
    -0.59
    POSITIVE LOGITS
    strength
    1.06
    package
    1.04
    pair
    1.04
    expression
    1.03
    service
    1.01
    surface
    0.99
    advertising
    0.99
    prem
    0.98
    serving
    0.98
    distance
    0.98
    Activations Density 0.052%

    No Known Activations