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. 6-RES-JB
    6. 18058
    Prev
    Next
    INDEX
    Explanations

    terms related to materials or structures that offer protection or durability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of resistance and proofing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPA
    -0.91
    reon
    -0.78
    atri
    -0.77
    gomery
    -0.74
    swick
    -0.73
    involved
    -0.73
    luence
    -0.71
    quart
    -0.71
    quist
    -0.71
    bourg
    -0.70
    POSITIVE LOGITS
     coating
    0.92
     insulated
    0.90
     fabrics
    0.89
     coat
    0.89
     polymer
    0.88
     waterproof
    0.84
     nylon
    0.83
     plastics
    0.82
     insulation
    0.81
     Coat
    0.80
    Activations Density 0.075%

    No Known Activations