© 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. 10489
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "pipe"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pipe."

    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
     contracting
    -0.66
     capt
    -0.63
     textbook
    -0.62
     Guild
    -0.61
     Hanson
    -0.60
     Forrest
    -0.59
     daylight
    -0.58
     Federal
    -0.58
     Somers
    -0.58
     fundraising
    -0.58
    POSITIVE LOGITS
    ipe
    4.30
    iped
    1.24
    iper
    1.18
    iping
    1.17
    peat
    1.11
    ipes
    1.09
    ipers
    1.08
     Pipe
    1.03
    ipeg
    0.98
    ip
    0.96
    Activations Density 0.011%

    No Known Activations