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. 8-RES-JB
    6. 19855
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms containing "IR"

    oai_token-act-pair · gpt-3.5-turbo

    references to Iranian organizations and terms related to Iran

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ethe
    -0.69
     Atl
    -0.68
    ifest
    -0.65
    ciating
    -0.62
    onym
    -0.62
    ça
    -0.61
    otion
    -0.61
     Pound
    -0.61
    xit
    -0.60
    ichi
    -0.59
    POSITIVE LOGITS
    FU
    0.97
    CLE
    0.95
    WIN
    0.94
    MED
    0.93
    ROR
    0.90
    ANGE
    0.89
    CU
    0.86
    ENA
    0.85
    ANG
    0.84
    OME
    0.82
    Activations Density 0.023%

    No Known Activations