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. 6-RES-JB
    6. 23194
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abbreviation "IR"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "IR", likely referring to infrared technology or a specific organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xit
    -0.71
     Bold
    -0.66
    coat
    -0.65
     Archdemon
    -0.64
     Pound
    -0.63
     Atl
    -0.63
     ç¥ŀ
    -0.63
    gaard
    -0.62
    amination
    -0.62
     Balkans
    -0.62
    POSITIVE LOGITS
    WIN
    1.04
    ROR
    0.99
    TY
    0.97
    FU
    0.96
    OME
    0.94
    MED
    0.89
    CLE
    0.87
    CU
    0.86
    LESS
    0.85
    WIND
    0.85
    Activations Density 0.014%

    No Known Activations