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. 24263
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating direction or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating navigation or directionality

    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
    iating
    -0.78
    cially
    -0.69
    alties
    -0.68
    aneously
    -0.67
     apart
    -0.66
    taboola
    -0.65
    ãģ®é
    -0.65
    iator
    -0.64
    bet
    -0.63
     loudly
    -0.61
    POSITIVE LOGITS
     Gallery
    1.22
     Contents
    1.08
     Top
    0.89
     top
    0.86
     homepage
    0.85
     Index
    0.85
     TOP
    0.82
     Main
    0.81
     Menu
    0.81
     Basics
    0.77
    Activations Density 0.037%

    No Known Activations