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. 1-RES-JB
    6. 18084
    Prev
    Next
    INDEX
    Explanations

    references to the ISO (International Organization for Standardization) 12312-2 standard

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ISO standards and certifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rill
    -0.89
    hips
    -0.88
    bones
    -0.86
    ships
    -0.79
    packs
    -0.78
    ãĥ©ãĥ³
    -0.77
    bone
    -0.77
    eez
    -0.76
    lain
    -0.76
    some
    -0.76
    POSITIVE LOGITS
     ISO
    1.34
    ISO
    1.22
    iso
    0.91
     iso
    0.89
     ASA
    0.80
    Hunt
    0.76
     SAN
    0.76
     nomine
    0.75
    CHR
    0.74
     Skydragon
    0.74
    Activations Density 0.012%

    No Known Activations