© 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. 1-RES-JB
    11. 14541
    Prev
    Next
    INDEX
    Explanations

    words related to fiscal matters or financial calculations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial and economic calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    href
    -0.79
     Mub
    -0.75
    kit
    -0.75
    adder
    -0.69
     Jacket
    -0.69
    pires
    -0.63
    eth
    -0.62
    plate
    -0.62
    essee
    -0.61
    arov
    -0.60
    POSITIVE LOGITS
    iscal
    1.40
    culated
    0.99
    kered
    0.90
    cul
    0.79
    culation
    0.78
    ounters
    0.78
    uracy
    0.76
    correct
    0.75
    mental
    0.72
     indisc
    0.72
    Activations Density 0.013%

    No Known Activations