© 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. 10472
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions or purchases made by individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bought."

    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
     Archdemon
    -0.82
    odor
    -0.72
    ankind
    -0.71
    Phys
    -0.70
    pmwiki
    -0.66
    ella
    -0.66
    eway
    -0.66
    inas
    -0.66
    ance
    -0.64
    of
    -0.60
    POSITIVE LOGITS
     bought
    1.02
     buying
    0.93
     buys
    0.85
     buy
    0.85
    iture
    0.84
     purchases
    0.84
     purchased
    0.83
     Gifts
    0.80
     Seym
    0.79
    ħĭ
    0.78
    Activations Density 0.017%

    No Known Activations