© 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. 9-RES-JB
    11. 10046
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Based on"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "based on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ura
    -0.79
    zon
    -0.73
    alla
    -0.69
    ifix
    -0.69
    apo
    -0.68
     hanged
    -0.67
    cca
    -0.67
     Nadu
    -0.66
    peat
    -0.66
    Daddy
    -0.65
    POSITIVE LOGITS
     observations
    0.99
     observation
    0.94
     principles
    0.93
     feedback
    0.91
     recommendations
    0.87
     assumptions
    0.87
     hears
    0.86
     anecdotal
    0.85
     findings
    0.85
     testimony
    0.81
    Activations Density 0.133%

    No Known Activations