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. 4563
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or transitions

    oai_token-act-pair · gpt-3.5-turbo
    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
    eful
    -0.74
    acea
    -0.67
    LOCK
    -0.67
    arest
    -0.66
    etary
    -0.64
    ounding
    -0.64
    iar
    -0.62
     unanswered
    -0.58
    bey
    -0.58
    hest
    -0.58
    POSITIVE LOGITS
     now
    1.10
     lately
    1.07
     nowadays
    1.07
     recently
    0.97
     suddenly
    0.95
     gradually
    0.90
     morphed
    0.87
    now
    0.87
     changed
    0.86
    uddenly
    0.83
    Activations Density 0.371%

    No Known Activations