© 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. 11-RES-JB
    6. 20647
    Prev
    Next
    INDEX
    Explanations

    tech companies and their product announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to technology companies and their product announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geries
    -0.73
    Topics
    -0.70
     comprehension
    -0.70
    onyms
    -0.70
    %%%%
    -0.68
    heid
    -0.67
    renheit
    -0.66
    enezuel
    -0.66
    Topic
    -0.65
    Reviewer
    -0.65
    POSITIVE LOGITS
     unveiled
    1.16
     announced
    1.14
     unveil
    1.10
     announce
    1.09
     releasing
    1.08
     partnered
    1.08
    announced
    1.04
     unveiling
    1.03
     release
    1.02
     teased
    1.02
    Activations Density 0.210%

    No Known Activations