© 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. 0-RES-JB
    11. 2064
    Prev
    Next
    INDEX
    Explanations

    key terms related to financial transactions or tax laws

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "FT" followed by numerical values

    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
     extermination
    -0.72
     ori
    -0.71
     dram
    -0.68
     Elvis
    -0.64
     Bohem
    -0.64
     Schwarzenegger
    -0.63
     escal
    -0.63
     anat
    -0.63
     overrun
    -0.62
     appeal
    -0.61
    POSITIVE LOGITS
    FT
    4.45
     FT
    1.84
    ft
    1.77
    BT
    1.49
    FF
    1.46
    FP
    1.37
    fts
    1.34
    FS
    1.31
    FC
    1.28
    PT
    1.25
    Activations Density 0.009%

    No Known Activations