© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5043
    Prev
    Next
    INDEX
    Explanations

    mentions of time durations, specifically short durations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" in various contexts

    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
     eru
    -0.68
     Anxiety
    -0.64
     Explosive
    -0.61
     umbrella
    -0.61
     inquiries
    -0.61
     Events
    -0.60
     negatives
    -0.59
     accelerated
    -0.58
     Esports
    -0.58
     allergies
    -0.57
    POSITIVE LOGITS
    rouse
    1.18
     few
    1.18
     couple
    1.16
     fortnight
    1.12
    urally
    1.04
     decade
    0.99
     la
    0.96
     bit
    0.96
    venge
    0.95
     week
    0.95
    Activations Density 0.126%

    No Known Activations