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. 9-RES-JB
    6. 9307
    Prev
    Next
    INDEX
    Explanations

    terms related to problems, issues, or controversies

    oai_token-act-pair · gpt-3.5-turbo

    complex words with multiple syllables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NCT
    -0.74
    \/\/
    -0.74
     Willow
    -0.66
     tidal
    -0.64
    ensional
    -0.64
    ¯
    -0.61
    ufact
    -0.60
     Constantine
    -0.58
    ovych
    -0.58
     Benz
    -0.58
    POSITIVE LOGITS
    rency
    0.94
    cled
    0.92
    cling
    0.77
    cius
    0.74
    ña
    0.73
    Browser
    0.71
    inence
    0.71
    brance
    0.70
     pestic
    0.70
    rences
    0.66
    Activations Density 0.133%

    No Known Activations