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. 1542
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    assertions about independence and self-sufficiency

    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
    izon
    -0.50
    LOS
    -0.44
    adelphia
    -0.44
    irement
    -0.44
     TODAY
    -0.42
     Marlins
    -0.42
    ibrary
    -0.41
    hematically
    -0.41
     McDonnell
    -0.40
     And
    -0.39
    POSITIVE LOGITS
     alike
    1.27
     respectively
    1.04
     thereof
    0.95
     accordingly
    0.87
     thereafter
    0.79
     thereto
    0.75
     therein
    0.67
    depending
    0.66
     versa
    0.61
     ensued
    0.59
    Activations Density 3.960%

    No Known Activations