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. 4905
    Prev
    Next
    INDEX
    Explanations

    a variety of diverse items or elements within a category

    oai_token-act-pair · gpt-3.5-turbo

    the concept of diversity or variety within different contexts

    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
     Dodd
    -0.71
    Hub
    -0.69
    Fe
    -0.69
    mit
    -0.66
    Gold
    -0.66
    eps
    -0.66
    BA
    -0.64
    IDA
    -0.62
    äºĶ
    -0.62
    Adam
    -0.62
    POSITIVE LOGITS
     ranges
    1.06
     range
    1.06
    finder
    0.95
    range
    0.92
    ahead
    0.78
    ensical
    0.74
     ranged
    0.73
     bour
    0.72
     Rover
    0.72
     lengths
    0.71
    Activations Density 0.017%

    No Known Activations