© 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. 0-RES-JB
    6. 16729
    Prev
    Next
    INDEX
    Explanations

    terms related to data and information technology infrastructure, specifically focusing on the concept of "load"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "load" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ti
    -0.77
     venue
    -0.72
     shaky
    -0.62
     professionally
    -0.61
     History
    -0.61
     conference
    -0.60
     commemor
    -0.60
     abs
    -0.59
     VI
    -0.59
     Freedom
    -0.59
    POSITIVE LOGITS
    oad
    4.91
    oaded
    2.51
    OAD
    1.40
    aunch
    1.12
    oop
    0.96
    obar
    0.95
    oxic
    0.95
    ocy
    0.94
    ibrary
    0.94
    ãĤĮ
    0.91
    Activations Density 0.015%

    No Known Activations