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. 210
    Prev
    Next
    INDEX
    Explanations

    the word "One" with various numbers after it

    oai_token-act-pair · gpt-3.5-turbo

    references to the HTC One smartphone series

    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
    imentary
    -0.76
     actionGroup
    -0.75
     srf
    -0.71
    rador
    -0.70
    lished
    -0.70
    NRS
    -0.68
    ruary
    -0.67
     exting
    -0.67
     plurality
    -0.67
    ãĤ°
    -0.66
    POSITIVE LOGITS
     Hundred
    1.04
    esan
    0.83
     Thousand
    0.83
     hundred
    0.80
     Piece
    0.76
     dimensional
    0.74
    horn
    0.73
     Percent
    0.72
     Month
    0.72
     Direction
    0.71
    Activations Density 0.028%

    No Known Activations