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. 2-RES-JB
    6. 16800
    Prev
    Next
    INDEX
    Explanations

    words related to technological functions or features

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of functionality in systems or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.98
    gas
    -0.76
    earth
    -0.72
    Pac
    -0.70
    yon
    -0.69
    Son
    -0.68
    kos
    -0.68
     Thousand
    -0.68
    ioxide
    -0.66
    vol
    -0.65
    POSITIVE LOGITS
     functionality
    1.00
    afety
    0.82
    witz
    0.78
     guiActiveUn
    0.77
    avascript
    0.76
    ality
    0.76
    ivity
    0.75
    unctions
    0.75
    matical
    0.75
    atility
    0.74
    Activations Density 0.011%

    No Known Activations