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. 11-RES-JB
    6. 18478
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming-related words

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes related to software development and project management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enriched
    -0.86
     eleph
    -0.85
     destro
    -0.85
     freezer
    -0.83
     guts
    -0.81
     rul
    -0.80
     migr
    -0.78
     landsl
    -0.78
     claws
    -0.78
     lungs
    -0.78
    POSITIVE LOGITS
    Although
    1.68
    Throughout
    1.67
    There
    1.66
    While
    1.66
    Before
    1.66
    When
    1.65
    During
    1.62
    Many
    1.62
    Since
    1.61
    Sometimes
    1.61
    Activations Density 0.182%

    No Known Activations