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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22337
    Prev
    Next
    INDEX
    Explanations

    multiplication and mathematical operations in text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mathematical operations, particularly multiplication and division

    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
    oho
    -0.85
    ALE
    -0.79
    cknowled
    -0.70
    nee
    -0.67
    rouse
    -0.64
    ELF
    -0.64
    bones
    -0.62
    cho
    -0.62
    twitch
    -0.62
    ä½ľ
    -0.62
    POSITIVE LOGITS
     multiplication
    1.07
     multiply
    1.06
    ithmetic
    0.91
     multiplying
    0.91
     multipl
    0.90
    Factor
    0.86
    multipl
    0.86
     subtract
    0.80
     fractions
    0.80
     exponentially
    0.80
    Activations Density 0.027%

    No Known Activations