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. 10904
    Prev
    Next
    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating accomplishments or milestones

    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
     replies
    -0.68
     preferred
    -0.68
    CI
    -0.62
     cant
    -0.62
     doesnt
    -0.62
     sul
    -0.60
     deviations
    -0.60
     hes
    -0.58
    ollah
    -0.58
     wont
    -0.57
    POSITIVE LOGITS
     date
    1.61
    date
    1.41
    wered
    1.29
    days
    1.08
    adies
    1.07
    ilers
    1.06
    ggles
    1.06
    ppers
    1.05
     coincide
    1.03
    asted
    1.02
    Activations Density 0.179%

    No Known Activations