© 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. 3-RES-JB
    11. 23215
    Prev
    Next
    INDEX
    Explanations

    references to NOAA (National Oceanic and Atmospheric Administration) locations or data

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific organizations and proper names related to scientific data and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thro
    -0.87
    atos
    -0.83
    ç
    -0.82
    coni
    -0.80
    athan
    -0.80
    pee
    -0.79
    aan
    -0.78
    agers
    -0.78
    ofi
    -0.78
    oner
    -0.77
    POSITIVE LOGITS
    ĨĴ
    0.77
     amplification
    0.74
     Fisheries
    0.73
     uncertainties
    0.69
    £ı
    0.67
     astronomers
    0.67
     NOAA
    0.65
    idth
    0.65
     livest
    0.65
    İĭ
    0.64
    Activations Density 0.021%

    No Known Activations