© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15819
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various topics like technology, healthcare, and global affairs

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals and topics related to social issues

    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
    ij士
    -0.66
    æĸ¹
    -0.61
    é¾įåĸļ士
    -0.60
    ioxide
    -0.59
    ãģ®ç
    -0.58
    ãĤ´ãĥ³
    -0.57
    senal
    -0.56
    å¦
    -0.56
    姫
    -0.55
    ettel
    -0.55
    POSITIVE LOGITS
     or
    0.61
    /
    0.56
     Morty
    0.53
    /
    0.50
    ico
    0.48
    âĢij
    0.47
     and
    0.47
    weed
    0.46
     buffalo
    0.46
     ..........
    0.45
    Activations Density 1.798%

    No Known Activations