© 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. 8-RES-JB
    11. 2602
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of cost or expenditure

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or pricing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ullivan
    -0.75
    vironment
    -0.73
    zinski
    -0.72
    venth
    -0.64
    Sand
    -0.64
    employment
    -0.64
    vous
    -0.63
    fw
    -0.62
    irtual
    -0.62
    intend
    -0.62
    POSITIVE LOGITS
     taxpayers
    1.11
     prohib
    1.04
    umed
    1.04
    lier
    0.95
    umers
    0.94
    liest
    0.90
    payers
    0.89
     savings
    0.88
     money
    0.87
     $
    0.86
    Activations Density 0.039%

    No Known Activations