© 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. 16324
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Less" in a series of text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a reduction or a decrease in quantity

    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
    è¦ļéĨĴ
    -0.67
     "{
    -0.64
    ãĤ±
    -0.64
    OCK
    -0.61
    kamp
    -0.61
    DATA
    -0.59
    TAIN
    -0.59
    GB
    -0.59
    ORN
    -0.59
    issance
    -0.58
    POSITIVE LOGITS
     than
    0.88
     Than
    0.85
    ened
    0.83
    erton
    0.78
    ening
    0.76
    ons
    0.73
    than
    0.68
    ensive
    0.68
    vasive
    0.68
    ente
    0.68
    Activations Density 0.026%

    No Known Activations