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. 9747
    Prev
    Next
    INDEX
    Explanations

    instances of variables within code snippets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "instance" in various contexts

    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
    sis
    -0.79
    sonian
    -0.72
    otine
    -0.66
    iage
    -0.65
    RANT
    -0.65
    ieu
    -0.64
    azines
    -0.64
    aptop
    -0.63
    psons
    -0.62
    aceous
    -0.61
    POSITIVE LOGITS
    als
    0.85
    leness
    0.79
    eering
    0.76
    rack
    0.76
    hedon
    0.74
    ally
    0.71
    ually
    0.71
    ele
    0.69
    Newsletter
    0.69
     Kut
    0.69
    Activations Density 0.050%

    No Known Activations