© 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. 2-RES-JB
    6. 18492
    Prev
    Next
    INDEX
    Explanations

    mentions of academic institutions and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scratches
    -0.68
    ::::::::
    -0.68
     emot
    -0.68
     gra
    -0.67
     dots
    -0.67
     idle
    -0.67
     bleed
    -0.66
    poke
    -0.65
     temptation
    -0.64
     yarn
    -0.64
    POSITIVE LOGITS
     chaired
    0.97
     Association
    0.88
     Society
    0.83
     headquartered
    0.83
     Universities
    0.83
     Colleges
    0.83
     Institute
    0.82
     Federation
    0.82
     presided
    0.79
     sponsoring
    0.78
    Activations Density 2.541%

    No Known Activations