© 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. 4-RES-JB
    6. 13577
    Prev
    Next
    INDEX
    Explanations

    words related to burdens or heavy responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "burden" used in various contexts

    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
    cium
    -0.70
    naissance
    -0.69
    specified
    -0.67
    confirmed
    -0.66
    */(
    -0.65
    encers
    -0.64
    chlor
    -0.63
    IFIC
    -0.62
    apeake
    -0.62
    mpeg
    -0.61
    POSITIVE LOGITS
     burden
    1.43
     burdens
    1.33
    lessly
    0.95
     burd
    0.93
     borne
    0.88
     load
    0.83
     loads
    0.81
    weights
    0.81
     levied
    0.80
    urden
    0.78
    Activations Density 0.017%

    No Known Activations