Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 4045
    Prev
    Next
    INDEX
    Explanations

    keywords related to mathematics

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematics and related educational concepts

    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
    ktop
    -0.69
     HRC
    -0.64
     flesh
    -0.63
    hyde
    -0.63
    views
    -0.62
     Corpse
    -0.61
     Sheridan
    -0.60
    utsche
    -0.60
    hold
    -0.59
    OPLE
    -0.59
    POSITIVE LOGITS
    matical
    1.26
    ieu
    1.10
    ilde
    1.07
    hemat
    1.05
    hematic
    1.05
    ilda
    1.01
    letes
    0.94
    mers
    0.93
    ias
    0.91
     equations
    0.89
    Activations Density 0.025%

    No Known Activations