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. 9-RES-JB
    6. 6251
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing a particular subject or concept as the central focus

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the concept of "everything" or "all-encompassing" ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •All the Features!

    No Comments

    Negative Logits
    rients
    -0.64
    bal
    -0.63
     Flavoring
    -0.62
    Arg
    -0.60
    DragonMagazine
    -0.60
    ridor
    -0.59
    Fight
    -0.59
    Fs
    -0.58
    é¾įå¥ij士
    -0.57
     Caption
    -0.56
    POSITIVE LOGITS
    uring
    1.18
    uding
    1.05
    ocating
    1.05
    usion
    0.98
    ergic
    0.93
    ayed
    0.89
    owing
    0.87
    ocated
    0.84
    iter
    0.81
    oy
    0.80
    Activations Density 0.054%

    No Known Activations