© 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. 7-RES-JB
    11. 3064
    Prev
    Next
    INDEX
    Explanations

    references or contexts related to the name "Newton"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'Newton' and related geographical mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.80
    EEP
    -0.77
    susp
    -0.72
    ansas
    -0.70
    pport
    -0.66
    toe
    -0.66
    llular
    -0.65
    acters
    -0.64
    ertility
    -0.63
    conservancy
    -0.62
    POSITIVE LOGITS
    ãĤ©
    0.78
     Scot
    0.77
     Scotia
    0.77
    arium
    0.73
    uits
    0.70
    DAQ
    0.69
     Newton
    0.68
    osal
    0.68
    icist
    0.67
    eers
    0.66
    Activations Density 0.062%

    No Known Activations