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. 1-RES-JB
    6. 15141
    Prev
    Next
    INDEX
    Explanations

    common action verbs

    oai_token-act-pair · gpt-3.5-turbo

    high-frequency function words that indicate structure and connection in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsy
    -0.55
    udic
    -0.53
    ãĤ¨ãĥ«
    -0.48
    åĬ
    -0.47
    clad
    -0.47
    EngineDebug
    -0.46
    igenous
    -0.46
    esque
    -0.46
    psey
    -0.45
    ê
    -0.45
    POSITIVE LOGITS
    cknowled
    0.58
     antioxid
    0.58
    terness
    0.56
     citiz
    0.55
     pse
    0.54
     Wanted
    0.53
     millenn
    0.52
     behavi
    0.51
     exha
    0.51
     blat
    0.50
    Activations Density 0.772%

    No Known Activations