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. 1-RES-JB
    6. 15082
    Prev
    Next
    INDEX
    Explanations

    references to computer graphics cards, particularly those related to the AMD Radeon series

    oai_token-act-pair · gpt-3.5-turbo

    references to specific graphics card brands and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icago
    -0.77
    mitt
    -0.76
    uter
    -0.71
    verages
    -0.69
    ply
    -0.68
     contag
    -0.67
    adequ
    -0.65
     bloom
    -0.65
    urai
    -0.64
    arette
    -0.64
    POSITIVE LOGITS
    eer
    0.96
    seys
    0.77
    LR
    0.75
    eers
    0.74
    tyard
    0.70
    ledge
    0.70
    ror
    0.69
    esses
    0.68
    lands
    0.67
    rary
    0.66
    Activations Density 0.012%

    No Known Activations