© 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. 0-RES-JB
    11. 17924
    Prev
    Next
    INDEX
    Explanations

    terms related to influential individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to influential individuals or concepts

    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
    plain
    -0.73
    mast
    -0.67
     pic
    -0.65
     versus
    -0.64
    KE
    -0.64
     Schedule
    -0.63
    can
    -0.63
     mode
    -0.62
    Lock
    -0.62
     recovery
    -0.62
    POSITIVE LOGITS
     influential
    3.33
     prominent
    1.42
     influ
    1.40
     seminal
    1.39
     prestigious
    1.37
     outspoken
    1.35
     influencing
    1.35
     powerful
    1.35
     influence
    1.34
     authoritative
    1.31
    Activations Density 0.013%

    No Known Activations