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. 22023
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical height

    oai_token-act-pair · gpt-3.5-turbo

    references to physical dimensions, specifically height

    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
    tical
    -0.83
    utical
    -0.80
    zsche
    -0.73
    BOOK
    -0.73
    ño
    -0.72
    ãģ¦
    -0.71
     Reloaded
    -0.66
    redo
    -0.66
    ctive
    -0.64
    ãĥ£
    -0.64
    POSITIVE LOGITS
     heights
    0.87
    ened
    0.87
    falls
    0.84
     height
    0.83
    rises
    0.82
     stature
    0.81
    ening
    0.81
     cliffs
    0.80
    fall
    0.77
    itudinal
    0.76
    Activations Density 0.019%

    No Known Activations