© 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. 10-RES-JB
    11. 944
    Prev
    Next
    INDEX
    Explanations

    geographical locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to locations and geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WATCHED
    -0.64
     partName
    -0.64
     messenger
    -0.57
     Metatron
    -0.56
     fist
    -0.56
     secretaries
    -0.55
     cloaked
    -0.54
    quished
    -0.54
     joke
    -0.54
     excuses
    -0.53
    POSITIVE LOGITS
    ingen
    0.99
    opolis
    0.98
    esville
    0.95
     Valley
    0.94
     Highlands
    0.94
     Township
    0.91
     valley
    0.91
    fecture
    0.90
    furt
    0.89
    ville
    0.88
    Activations Density 0.171%

    No Known Activations