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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18852
    Prev
    Next
    INDEX
    Explanations

    words related to card games

    oai_token-act-pair · gpt-3.5-turbo

    words related to "ard" such as names, organizations, or activities

    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
    ĸļ
    -1.00
    ĺħ
    -0.77
    ãĤ´ãĥ³
    -0.71
     tremend
    -0.69
    uters
    -0.69
     Pastebin
    -0.68
    PLA
    -0.68
     heels
    -0.66
    ongyang
    -0.66
    POL
    -0.65
    POSITIVE LOGITS
    ard
    1.23
    ards
    1.06
    ragon
    1.04
    rill
    0.97
    orf
    0.91
    hart
    0.90
    igans
    0.88
    ling
    0.86
    lings
    0.86
    ARD
    0.85
    Activations Density 0.012%

    No Known Activations