© 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. 2-RES-JB
    11. 9080
    Prev
    Next
    INDEX
    Explanations

    phrases related to expansion, expenses, and budgeting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expansion or increases in context, particularly in topics concerning healthcare or resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    warts
    -0.72
    tie
    -0.70
    footed
    -0.70
    ball
    -0.69
    wolf
    -0.67
    BOOK
    -0.65
    MET
    -0.65
    kus
    -0.65
    milo
    -0.63
    geist
    -0.63
    POSITIVE LOGITS
    ulsion
    1.29
    onential
    1.29
    onent
    1.16
    anded
    1.11
    orters
    1.10
    ansion
    1.10
    ittal
    1.02
    ensive
    1.01
    osed
    1.01
    anding
    1.01
    Activations Density 0.003%

    No Known Activations