© 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. 6-RES-JB
    11. 12830
    Prev
    Next
    INDEX
    Explanations

    keywords related to burdens or responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to burdens or difficulties faced by individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.77
    apeake
    -0.75
    naissance
    -0.72
    wagen
    -0.71
    mpeg
    -0.71
    */(
    -0.69
    ovies
    -0.68
    guyen
    -0.68
    ilater
    -0.68
    chlor
    -0.68
    POSITIVE LOGITS
     burden
    1.36
     burdens
    1.28
     burd
    0.95
     borne
    0.89
     levied
    0.86
     imposed
    0.82
     loads
    0.81
     load
    0.81
    lessly
    0.80
     incurred
    0.80
    Activations Density 0.043%

    No Known Activations