© 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. 10-RES-JB
    11. 10060
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or payments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating payments or financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    felt
    -0.78
    AAAAAAAA
    -0.72
    sectional
    -0.66
    typ
    -0.64
    furt
    -0.62
    ItemThumbnailImage
    -0.62
     awaited
    -0.62
    soType
    -0.61
    hew
    -0.60
    worldly
    -0.59
    POSITIVE LOGITS
     acquire
    1.15
     compensate
    1.09
     maintain
    1.07
     operate
    1.06
     settle
    1.04
     advertise
    1.00
     insure
    0.98
     administer
    0.98
     assemble
    0.98
     participate
    0.97
    Activations Density 0.084%

    No Known Activations