© 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 EvalsExportsinterp-engineNEWAPI 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. 15210
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions or notes

    oai_token-act-pair · gpt-3.5-turbo

    references to bank notes

    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
     endless
    -0.67
     breast
    -0.67
     material
    -0.66
     ultimate
    -0.66
     intervention
    -0.64
     answers
    -0.63
     bos
    -0.63
     ent
    -0.61
     Dug
    -0.61
     overload
    -0.60
    POSITIVE LOGITS
    note
    4.09
    notes
    2.38
    notice
    1.44
    NOTE
    1.43
    Footnote
    1.20
    edit
    1.18
    emphasis
    1.18
    deb
    1.17
    setting
    1.12
    Note
    1.11
    Activations Density 0.028%

    No Known Activations