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. 13162
    Prev
    Next
    INDEX
    Explanations

    technical terms related to hardware and software features and specifications

    oai_token-act-pair · gpt-3.5-turbo

    terminology associated with technology and product performance

    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
    Anyway
    -0.77
    arently
    -0.76
    pmwiki
    -0.75
    xious
    -0.72
     Anyway
    -0.72
    identally
    -0.71
    */(
    -0.69
    inventoryQuantity
    -0.69
    bably
    -0.69
     strang
    -0.69
    POSITIVE LOGITS
    ®,
    1.03
     ensures
    0.99
    ®
    0.94
     delivers
    0.93
     featuring
    0.89
     spanning
    0.87
    âĦ¢
    0.84
     guaranteeing
    0.83
     unparalleled
    0.83
     ensuring
    0.82
    Activations Density 0.582%

    No Known Activations