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. 24452
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and medical terms related to the nervous system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to turkeys and phosphates

    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
     showc
    -0.85
    iola
    -0.72
    ardo
    -0.71
    ardi
    -0.70
     dexter
    -0.69
    fried
    -0.68
    ERT
    -0.68
     sidel
    -0.65
     anesthesia
    -0.64
    ilda
    -0.63
    POSITIVE LOGITS
    tur
    0.83
     Bie
    0.81
    gery
    0.79
    igslist
    0.74
    geries
    0.74
    ku
    0.74
    levard
    0.73
     Fortress
    0.73
    ĸļ
    0.71
    ngth
    0.69
    Activations Density 0.025%

    No Known Activations