© 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. 3-RES-JB
    11. 23080
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and reimbursements

    oai_token-act-pair · gpt-3.5-turbo

    references to financial obligations or payments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.82
     disarm
    -0.70
    \\\\\\\\
    -0.67
    gha
    -0.63
    CHAR
    -0.60
     DH
    -0.59
    Young
    -0.59
    bang
    -0.58
    bees
    -0.58
    humans
    -0.58
    POSITIVE LOGITS
    omething
    1.03
    ments
    0.98
    hower
    0.95
    poons
    0.91
    uled
    0.90
    pring
    0.89
    leeve
    0.82
    clerosis
    0.79
    ateral
    0.78
    mith
    0.76
    Activations Density 0.024%

    No Known Activations