© 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. 7-RES-JB
    6. 15303
    Prev
    Next
    INDEX
    Explanations

    phrases related to natural gas and specific countries like Brunei

    oai_token-act-pair · gpt-3.5-turbo

    references to liquefied natural gas and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Redemption
    -0.72
    -+-+-+-+
    -0.70
     sled
    -0.69
     Chiefs
    -0.68
     mast
    -0.66
     Mouse
    -0.65
     Panda
    -0.64
     Crimson
    -0.64
     Shogun
    -0.63
     stump
    -0.63
    POSITIVE LOGITS
    afort
    1.11
    emark
    1.03
    eln
    0.97
    rael
    0.95
    heed
    0.91
    ere
    0.91
    lling
    0.91
    ette
    0.90
    elia
    0.89
    ller
    0.88
    Activations Density 0.077%

    No Known Activations