Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 15927
    Prev
    Next
    INDEX
    Explanations

    phrases related to durations of time

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Edit
    -0.68
    Anim
    -0.66
    gow
    -0.65
     âĶľ
    -0.61
    cards
    -0.60
    igne
    -0.60
    ierrez
    -0.60
    nces
    -0.59
    adobe
    -0.56
    achu
    -0.55
    POSITIVE LOGITS
     dozen
    1.71
    dozen
    1.52
     decade
    1.50
     hundred
    1.42
     thousand
    1.40
     century
    1.34
     month
    1.25
     quarter
    1.22
     million
    1.22
     year
    1.20
    Activations Density 0.058%

    No Known Activations