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. 11-RES-JB
    6. 10556
    Prev
    Next
    INDEX
    Explanations

    descriptions of products and their features

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the availability or presentation of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    benef
    -0.67
    maxwell
    -0.67
     Valley
    -0.67
    eur
    -0.62
     Writers
    -0.61
    laus
    -0.60
    pedia
    -0.60
    orthodox
    -0.60
    eering
    -0.59
    oris
    -0.59
    POSITIVE LOGITS
     equipped
    1.27
     packaged
    1.16
     bundled
    1.08
    equipped
    0.97
     loaded
    0.92
     stocked
    0.92
     furnished
    0.92
     fitted
    0.91
     packed
    0.89
     primed
    0.87
    Activations Density 0.064%

    No Known Activations