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. 21518
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to technical specifications or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters or acronyms that appear to be technical or code-related terms

    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
     toile
    -0.75
     Vaugh
    -0.71
     questioning
    -0.62
     CBI
    -0.56
     Huawei
    -0.56
    perse
    -0.55
    sheet
    -0.55
     [*]
    -0.54
    redo
    -0.54
    taboola
    -0.53
    POSITIVE LOGITS
    intosh
    0.95
    ufact
    0.89
    arella
    0.79
    htar
    0.79
    ouf
    0.76
    angelo
    0.74
    gage
    0.72
    ONEY
    0.71
    umenthal
    0.71
    hof
    0.70
    Activations Density 0.624%

    No Known Activations