© 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. 1-RES-JB
    6. 22754
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location or institution, particularly "Augusta."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Augusta, Maine, and related contexts, particularly in education and athletics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hood
    -0.83
     partic
    -0.75
    naire
    -0.71
    isan
    -0.67
    aired
    -0.65
     cinematic
    -0.64
    haul
    -0.64
    lining
    -0.64
    bon
    -0.63
    iddled
    -0.62
    POSITIVE LOGITS
    ADRA
    0.85
    dylib
    0.83
     Rex
    0.78
    conservancy
    0.78
    pta
    0.76
    ESCO
    0.76
     Apart
    0.73
     Britann
    0.72
    apolis
    0.70
    legram
    0.70
    Activations Density 0.036%

    No Known Activations