© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17924
    Prev
    Next
    INDEX
    Explanations

    mentions of financial profit or earnings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to profit and financial gain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.75
    confirmed
    -0.67
    ocally
    -0.67
     Sturgeon
    -0.65
    thia
    -0.64
    pell
    -0.64
     womb
    -0.63
    OG
    -0.62
    cling
    -0.62
    nu
    -0.62
    POSITIVE LOGITS
     margins
    1.12
     margin
    1.05
     profit
    0.95
    ably
    0.93
    ulent
    0.86
     profits
    0.86
     motive
    0.86
     Profit
    0.85
     earnings
    0.80
    iciary
    0.76
    Activations Density 0.012%

    No Known Activations