© 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. 7062
    Prev
    Next
    INDEX
    Explanations

    references to the subject of mathematics

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematics and related topics

    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
     Sov
    -0.78
    OPLE
    -0.71
    views
    -0.69
    lease
    -0.65
    ovo
    -0.63
    ————————
    -0.63
    ktop
    -0.62
    utsche
    -0.62
     Corpse
    -0.60
     Hond
    -0.59
    POSITIVE LOGITS
    matical
    1.15
    hematic
    1.07
    hemat
    1.01
    ilda
    1.01
    ieu
    0.95
    ilde
    0.90
     equations
    0.90
     homework
    0.85
    STEM
    0.85
     algebra
    0.84
    Activations Density 0.035%

    No Known Activations