© 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. 2-RES-JB
    11. 15742
    Prev
    Next
    INDEX
    Explanations

    financial transactions or actions related to reimbursement

    oai_token-act-pair · gpt-3.5-turbo

    past participles and verb forms related to reimbursement and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vari
    -0.71
    rooms
    -0.68
     nest
    -0.68
     grass
    -0.66
     nests
    -0.65
     iP
    -0.65
    ENN
    -0.64
     indoors
    -0.63
    amy
    -0.63
    bott
    -0.62
    POSITIVE LOGITS
    ursed
    0.83
    payers
    0.77
     restitution
    0.74
     levied
    0.72
     confidentiality
    0.71
    awaru
    0.70
     mediation
    0.69
     invoice
    0.69
     grace
    0.68
     reimbursement
    0.68
    Activations Density 0.137%

    No Known Activations