© 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. 9-RES-JB
    11. 3184
    Prev
    Next
    INDEX
    Explanations

    terms related to specific locations or establishments with some level of significance or controversy

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific social or cultural groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ernels
    -0.86
     Thumbnails
    -0.85
    ouls
    -0.85
    inctions
    -0.82
     Statements
    -0.82
     Shards
    -0.81
     Characters
    -0.81
    brids
    -0.80
     Zombies
    -0.80
     Guests
    -0.78
    POSITIVE LOGITS
     clinic
    1.17
     salon
    1.06
     cafe
    1.03
     motel
    1.02
    ominium
    0.99
     fundraiser
    0.99
     dealership
    0.99
     restaurant
    0.98
     seminar
    0.98
     contractor
    0.97
    Activations Density 0.479%

    No Known Activations