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. 4-RES-JB
    6. 18256
    Prev
    Next
    INDEX
    Explanations

    phrases related to being questioned or asked about various topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "about."

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

    No Comments

    Negative Logits
    rift
    -0.92
    à¥
    -0.82
    gallery
    -0.79
    OGR
    -0.75
    ³³³³³³³³³³³³³³³³
    -0.72
    SS
    -0.68
    ³³³³
    -0.68
    ////////////////////////////////
    -0.67
    =-=-=-=-=-=-=-=-
    -0.67
    chens
    -0.67
    POSITIVE LOGITS
    ials
    0.77
     reforming
    0.76
     whether
    0.73
     how
    0.71
    ļéĨĴ
    0.71
     reducing
    0.68
     bund
    0.67
     halfway
    0.66
     eliminating
    0.66
     topics
    0.65
    Activations Density 0.109%

    No Known Activations