© 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. 11-RES-JB
    11. 17591
    Prev
    Next
    INDEX
    Explanations

    specific mentions of locations/events and people interconnected through details of daily life activities

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating location or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Someone
    -0.68
    Warning
    -0.68
    someone
    -0.67
    Saudi
    -0.65
    Enlarge
    -0.65
    pmwiki
    -0.64
    ettel
    -0.62
    Elsa
    -0.62
    Unless
    -0.62
    Italy
    -0.62
    POSITIVE LOGITS
     Historic
    0.80
     Visit
    0.80
     the
    0.77
     Headquarters
    0.76
     Ago
    0.73
     Alloy
    0.73
     Refuge
    0.73
     Applied
    0.73
     Horizons
    0.73
     Recreation
    0.72
    Activations Density 0.328%

    No Known Activations