© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14015
    Prev
    Next
    INDEX
    Explanations

    monetary values and percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical expressions and figures involving monetary amounts or quantities

    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
     lag
    -0.64
    eries
    -0.62
     inconsistency
    -0.60
    igning
    -0.59
    wrapper
    -0.59
     Views
    -0.58
    ongyang
    -0.58
    Rating
    -0.56
    Primary
    -0.55
    bender
    -0.55
    POSITIVE LOGITS
     1000
    1.05
     400
    1.03
    1000
    1.03
     500
    1.00
     thousands
    0.99
     200
    0.98
    300
    0.98
     300
    0.97
     hundred
    0.97
    200
    0.96
    Activations Density 0.078%

    No Known Activations