© 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. 6-RES-JB
    11. 17189
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, especially "Anaheim" and "Irvine"

    oai_token-act-pair · gpt-3.5-turbo

    names of geographical locations and sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ombo
    -0.82
     ease
    -0.75
    Ö¼
    -0.74
    bered
    -0.70
    pees
    -0.67
    entary
    -0.67
    pee
    -0.66
    bley
    -0.66
    ty
    -0.64
    everal
    -0.64
    POSITIVE LOGITS
     Ducks
    1.33
    heim
    0.97
     Anaheim
    0.87
    stadt
    0.79
    unci
    0.74
    apolis
    0.70
    uno
    0.70
    liga
    0.68
    shire
    0.67
     Peninsula
    0.67
    Activations Density 0.047%

    No Known Activations