© 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. 0-RES-JB
    11. 2871
    Prev
    Next
    INDEX
    Explanations

    huge quantities or monetary values

    oai_token-act-pair · gpt-3.5-turbo

    references to large numerical values, specifically those related to "million."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Appearance
    -0.65
    adh
    -0.64
    ourn
    -0.64
    Attach
    -0.64
    ework
    -0.62
    Finish
    -0.59
    Accessory
    -0.59
    aways
    -0.58
     apt
    -0.58
     Prompt
    -0.57
    POSITIVE LOGITS
     million
    3.14
     billion
    2.45
    million
    2.42
     Million
    2.24
     thousand
    2.18
     crore
    2.07
     millions
    1.90
    billion
    1.89
     trillion
    1.85
     lakh
    1.78
    Activations Density 0.040%

    No Known Activations