© 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. 1-RES-JB
    11. 14421
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning or related to "observers"

    oai_token-act-pair · gpt-3.5-turbo

    the term "observers" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    street
    -0.75
    Family
    -0.65
    GET
    -0.65
    eways
    -0.64
     Duchess
    -0.64
    Customer
    -0.64
    Hom
    -0.63
    Bio
    -0.62
    Interstitial
    -0.61
    raz
    -0.61
    POSITIVE LOGITS
     observers
    1.40
     observer
    1.32
     wat
    1.07
    acers
    0.88
     onlook
    0.87
    opol
    0.81
     observing
    0.79
    insk
    0.78
     rejoice
    0.78
    ocular
    0.76
    Activations Density 0.010%

    No Known Activations