© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 507
    Prev
    Next
    INDEX
    Explanations

    the word "revenue"

    oai_token-act-pair · gpt-4-turbo

    instances of the word "revenue"

    oai_token-act-pair · gpt-3.5-turbo

    references to revenue

    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
    ovie
    -0.73
     Lob
    -0.71
    uran
    -0.71
    otin
    -0.71
     Wond
    -0.69
    called
    -0.65
    opol
    -0.63
    te
    -0.62
    \/\/
    -0.61
    OVA
    -0.60
    POSITIVE LOGITS
     revenue
    1.04
     revenues
    1.02
    interstitial
    0.95
     Revenue
    0.93
     receipts
    0.90
     streams
    0.89
     expenditure
    0.81
     income
    0.77
     Income
    0.77
     monet
    0.76
    Activations Density 0.008%

    No Known Activations