© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10369
    Prev
    Next
    INDEX
    Explanations

    the word "hang" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social gatherings or casual interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceptive
    -0.71
    sama
    -0.64
    index
    -0.63
    ugen
    -0.63
    ducers
    -0.63
    saw
    -0.62
     Machina
    -0.62
    andowski
    -0.62
    transform
    -0.62
     TABLE
    -0.61
    POSITIVE LOGITS
     hang
    3.81
     hangs
    2.21
     Hang
    2.10
     hung
    2.06
     hanging
    1.95
    hang
    1.89
     hanged
    1.56
     haunt
    1.32
     cling
    1.13
     attach
    1.04
    Activations Density 0.007%

    No Known Activations