© 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. 860
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "at least"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "at."

    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
    Sense
    -0.64
    erness
    -0.59
    itivity
    -0.58
    WER
    -0.56
    eria
    -0.54
    encer
    -0.53
    uchs
    -0.52
    SHIP
    -0.52
    available
    -0.52
    alities
    -0.52
    POSITIVE LOGITS
     least
    1.85
    onement
    1.24
    mosp
    1.02
     worst
    1.00
     lest
    0.99
    yp
    0.96
    roph
    0.95
     minimum
    0.94
     best
    0.93
    oning
    0.86
    Activations Density 0.071%

    No Known Activations