© 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. 11-RES-JB
    11. 20526
    Prev
    Next
    INDEX
    Explanations

    references to availability or access to products or services

    oai_token-act-pair · gpt-3.5-turbo

    references to food and dining experiences

    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
    £ı
    -0.88
    MpServer
    -0.87
    quickShipAvailable
    -0.82
     retracted
    -0.82
     contradicted
    -0.71
    modified
    -0.70
     Journals
    -0.69
    İĭ
    -0.67
    âĸĪâĸĪâĸĪâĸĪ
    -0.66
     Journalism
    -0.66
    POSITIVE LOGITS
     snag
    1.40
     enjoy
    1.14
     indulge
    1.08
     celebrate
    1.07
     partake
    1.07
     nab
    1.06
     grab
    1.01
     rejoice
    1.00
     watch
    1.00
     feast
    0.99
    Activations Density 0.289%

    No Known Activations