© 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. 9-RES-JB
    11. 2256
    Prev
    Next
    INDEX
    Explanations

    words related to generating income or revenue

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yer
    -0.74
    nee
    -0.73
    gerald
    -0.71
    say
    -0.70
    hai
    -0.70
    mare
    -0.66
    imation
    -0.63
    define
    -0.63
    haus
    -0.62
    aryn
    -0.62
    POSITIVE LOGITS
     revenue
    0.92
     electricity
    0.91
     income
    0.85
    vernment
    0.80
     revenues
    0.79
     Revenue
    0.78
     generated
    0.77
     generate
    0.75
     generates
    0.74
     kWh
    0.71
    Activations Density 0.051%

    No Known Activations