© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1846
    Prev
    Next
    INDEX
    Explanations

    phrases related to places and institutions, especially prestigious ones

    oai_token-act-pair · gpt-3.5-turbo

    references to reputable or prestigious institutions and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    escription
    -0.83
    ãĥīãĥ©ãĤ´ãĥ³
    -0.80
    imental
    -0.77
    reci
    -0.76
    ###
    -0.76
    opsis
    -0.72
    ItemImage
    -0.72
     sightings
    -0.71
    struction
    -0.70
     fracture
    -0.67
    POSITIVE LOGITS
     reputable
    1.01
     university
    0.83
     hotels
    0.80
     trusted
    0.80
     boutique
    0.78
     Doctors
    0.77
     provider
    0.77
     Bank
    0.76
     Starbucks
    0.75
     nearby
    0.75
    Activations Density 0.709%

    No Known Activations