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. 9930
    Prev
    Next
    INDEX
    Explanations

    titles or specific phrases related to stories, questions, or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    references to stories and questions, particularly in the context of children's literature and related topics

    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
    ously
    -0.76
    arb
    -0.74
     exception
    -0.70
    activity
    -0.67
     republican
    -0.66
    rolog
    -0.65
     forestry
    -0.65
    livion
    -0.64
    ris
    -0.64
    atively
    -0.64
    POSITIVE LOGITS
     Advice
    1.06
     Parties
    1.06
     Characters
    1.06
     Ago
    1.04
     Shots
    1.04
     Places
    1.02
     Against
    1.01
     Dates
    0.99
     Without
    0.98
     Ahead
    0.98
    Activations Density 0.138%

    No Known Activations