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. 488
    Prev
    Next
    INDEX
    Explanations

    references to publications in journals or studies

    oai_token-act-pair · gpt-3.5-turbo

    instances of "published" referring to research studies or findings

    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
    lua
    -0.64
    nel
    -0.63
    roo
    -0.62
    xa
    -0.60
    assian
    -0.60
    ginx
    -0.59
    nea
    -0.58
    icons
    -0.57
    poke
    -0.56
    bones
    -0.55
    POSITIVE LOGITS
     anonymously
    1.04
     online
    1.01
     excerpts
    0.95
     elsewhere
    0.89
     yesterday
    0.89
    lishing
    0.87
    online
    0.83
     Monday
    0.82
     Feb
    0.79
     Sept
    0.79
    Activations Density 0.043%

    No Known Activations