© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 393
    Prev
    Next
    INDEX
    Explanations

    words related to weight classes in sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weight classes in sports and the word 'Wednesday.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.72
    imil
    -0.64
    INAL
    -0.63
    bably
    -0.63
    inance
    -0.63
    displayText
    -0.62
     understatement
    -0.61
    ixel
    -0.61
    URI
    -0.61
    inx
    -0.60
    POSITIVE LOGITS
    brook
    0.77
    burg
    0.76
    pool
    0.74
    mere
    0.73
    ipeg
    0.73
    fleet
    0.72
    stock
    0.72
    haven
    0.71
    eston
    0.71
    bury
    0.69
    Activations Density 0.163%

    No Known Activations