© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18512
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts, specifically calculus

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematical concepts, particularly calculus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aging
    -0.92
    age
    -0.83
    agraph
    -0.80
    fter
    -0.80
    fters
    -0.79
    acking
    -0.78
    yll
    -0.78
    ages
    -0.78
    inent
    -0.77
    eting
    -0.76
    POSITIVE LOGITS
    culus
    0.89
     calculus
    0.80
    REDACTED
    0.80
     Nieto
    0.79
     Magnus
    0.78
     Typh
    0.73
     Remastered
    0.70
     Bolt
    0.67
    quished
    0.67
     Lash
    0.67
    Activations Density 0.038%

    No Known Activations