© 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. 6-RES-JB
    11. 10759
    Prev
    Next
    INDEX
    Explanations

    mentions of spending money on various items, services, or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "spend" or its variations related to financial expenditures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.88
    SourceFile
    -0.85
    soDeliveryDate
    -0.83
    externalActionCode
    -0.76
    ONSORED
    -0.71
    zynski
    -0.71
     CLSID
    -0.71
    ///
    -0.70
    ress
    -0.68
    ector
    -0.66
    POSITIVE LOGITS
     behalf
    1.03
     frivol
    0.98
     acquiring
    0.85
     infrastructure
    0.83
     upkeep
    0.82
     extras
    0.79
     necessities
    0.77
     essentials
    0.77
     frivolous
    0.76
     beaut
    0.76
    Activations Density 0.056%

    No Known Activations