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. 3-RES-JB
    6. 11814
    Prev
    Next
    INDEX
    Explanations

    descriptions of things that are insubstantial or in scarce quantity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scarcity or limited quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     screws
    -0.75
     builder
    -0.71
    gdala
    -0.65
     bottleneck
    -0.65
     gateway
    -0.64
     junction
    -0.63
     threshold
    -0.62
     parole
    -0.62
     screw
    -0.61
     submarine
    -0.60
    POSITIVE LOGITS
    umes
    0.95
    ensibly
    0.91
    milo
    0.87
    natureconservancy
    0.84
    iture
    0.81
    itures
    0.81
    idas
    0.80
    rils
    0.78
    ords
    0.78
    icles
    0.78
    Activations Density 0.024%

    No Known Activations