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. 10-RES-JB
    6. 11805
    Prev
    Next
    INDEX
    Explanations

    prompts asking users to confirm they are not robots by checking a box or performing an action

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢİ
    -0.83
     gravy
    -0.70
    ways
    -0.63
     adj
    -0.59
     adv
    -0.59
     tact
    -0.58
    kaya
    -0.57
    imer
    -0.57
     tert
    -0.55
    itional
    -0.55
    POSITIVE LOGITS
     Invalid
    1.14
     Copy
    0.66
    Invalid
    0.65
     è£ıè
    0.64
    ItemTracker
    0.62
    Submit
    0.62
     Please
    0.61
     Errors
    0.61
    perture
    0.60
     Thumbnails
    0.59
    Activations Density 0.012%

    No Known Activations