© 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. 2615
    Prev
    Next
    INDEX
    Explanations

    words related to the term "bs"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "bs" (bytes or bits) and the context in which they are discussed

    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
    MENTS
    -0.66
     Vie
    -0.63
     delinquent
    -0.62
    MENT
    -0.62
    RELATED
    -0.62
    PRE
    -0.61
     Cooperation
    -0.60
    SIGN
    -0.60
    OPLE
    -0.60
    Sund
    -0.59
    POSITIVE LOGITS
    hirt
    1.18
    ettings
    1.16
    erver
    1.14
    poons
    1.07
    poon
    1.07
    ites
    1.06
    bs
    1.04
    paces
    1.03
    ocket
    1.02
    leep
    1.02
    Activations Density 0.023%

    No Known Activations