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. 17636
    Prev
    Next
    INDEX
    Explanations

    birthplaces and birthdates of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    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
    ologies
    -0.76
     Extend
    -0.76
    lag
    -0.73
    Includes
    -0.71
    Duration
    -0.67
     Which
    -0.66
    rates
    -0.66
    lies
    -0.66
     Compare
    -0.65
    ¨
    -0.64
    POSITIVE LOGITS
     born
    1.56
     diagnosed
    1.19
     baptized
    1.13
     arrested
    1.13
     sentenced
    1.10
     assassinated
    1.09
     recruited
    1.08
     murdered
    1.07
     ordained
    1.07
     bitten
    1.06
    Activations Density 0.218%

    No Known Activations