© 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. 10-RES-JB
    11. 10161
    Prev
    Next
    INDEX
    Explanations

    references to the name "Noah"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Noah," along with related content about individuals named Noah

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omething
    -0.99
    prus
    -0.89
    anova
    -0.82
    tone
    -0.81
    stan
    -0.81
    tones
    -0.80
    note
    -0.77
    fax
    -0.76
    netic
    -0.75
    wagen
    -0.73
    POSITIVE LOGITS
     Lincoln
    0.87
    ishly
    0.77
     butter
    0.74
     allergy
    0.73
    zing
    0.69
    erella
    0.68
     peanut
    0.67
    onom
    0.67
    9999
    0.67
     Abrams
    0.66
    Activations Density 0.088%

    No Known Activations