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. 22952
    Prev
    Next
    INDEX
    Explanations

    the word "is" followed by various descriptions

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases beginning with "is" that indicate assertions or definitions

    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
    otte
    -0.80
    Numbers
    -0.75
    arette
    -0.67
    arella
    -0.66
    actory
    -0.64
    rodu
    -0.64
    rongh
    -0.63
    oided
    -0.62
    ievers
    -0.61
    iation
    -0.59
    POSITIVE LOGITS
     why
    1.58
    why
    1.09
     understandable
    1.07
     ironic
    1.04
     WHY
    1.04
     presumably
    0.96
     admittedly
    0.96
     basically
    0.94
     exactly
    0.94
     what
    0.91
    Activations Density 0.146%

    No Known Activations