© 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. 0-RES-JB
    11. 12049
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or buying items

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary transactions or purchases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylon
    -0.64
    hap
    -0.60
    lip
    -0.60
    oliath
    -0.59
    erb
    -0.59
    thro
    -0.58
    mask
    -0.58
     Stab
    -0.57
    uddle
    -0.57
     prog
    -0.57
    POSITIVE LOGITS
     purchases
    3.65
     buys
    2.12
     purchase
    1.97
     purchasing
    1.90
     acquisitions
    1.79
     purch
    1.73
     purchased
    1.71
     Purch
    1.66
     shipments
    1.62
     buying
    1.60
    Activations Density 0.015%

    No Known Activations