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. 9-RES-JB
    6. 20474
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with the word "with"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    span
    -0.73
    hops
    -0.65
    sov
    -0.65
    other
    -0.64
    oslav
    -0.63
     differed
    -0.62
    âĹ¼
    -0.62
    Other
    -0.62
    involved
    -0.61
    accompan
    -0.61
    POSITIVE LOGITS
     respect
    0.84
    draw
    0.83
     basics
    0.77
     regards
    0.77
     scratch
    0.74
     apologies
    0.74
     breakfast
    0.73
     a
    0.71
    stood
    0.70
     minimal
    0.69
    Activations Density 0.065%

    No Known Activations