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. 2-RES-JB
    6. 20562
    Prev
    Next
    INDEX
    Explanations

    phrases related to trailers or previews

    oai_token-act-pair · gpt-3.5-turbo

    words related to trailers and transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.81
    lihood
    -0.73
    CLUD
    -0.71
    manship
    -0.69
    forth
    -0.66
     Mortal
    -0.65
     ellipt
    -0.61
     unconditional
    -0.61
     author
    -0.60
    lain
    -0.59
    POSITIVE LOGITS
    verse
    0.93
    ffic
    0.92
    quel
    0.91
    Tra
    0.86
    itored
    0.85
    pped
    0.84
    pping
    0.82
    pling
    0.80
    pez
    0.79
    isy
    0.79
    Activations Density 0.007%

    No Known Activations