© 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. 10731
    Prev
    Next
    INDEX
    Explanations

    phrases related to large quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that repeat the word "of" indicating a focus on quantity or inclusion

    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
    acus
    -0.73
    dayName
    -0.73
    EStream
    -0.73
    ħĭ
    -0.69
    epad
    -0.69
    ļéĨĴ
    -0.67
    essage
    -0.66
    berus
    -0.65
    xit
    -0.65
    daq
    -0.64
    POSITIVE LOGITS
     times
    1.35
     people
    1.23
     folks
    1.13
     commenters
    1.08
     commentators
    1.04
     us
    1.03
     peoples
    0.99
     reviewers
    0.99
     things
    0.97
     guys
    0.96
    Activations Density 0.124%

    No Known Activations