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. 7-RES-JB
    6. 22430
    Prev
    Next
    INDEX
    Explanations

    the first name "Winston" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Winston."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĦ
    -0.73
     mileage
    -0.70
    cules
    -0.69
    Magikarp
    -0.69
    gdala
    -0.68
    ÃįÃį
    -0.68
    giving
    -0.65
    isons
    -0.64
    holders
    -0.64
    give
    -0.63
    POSITIVE LOGITS
     Churchill
    1.08
     Salem
    0.80
    ishing
    0.79
    enberg
    0.76
     Peters
    0.74
    raft
    0.73
    ers
    0.70
    ufact
    0.70
    er
    0.69
    ilant
    0.68
    Activations Density 0.055%

    No Known Activations