© 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. 17412
    Prev
    Next
    INDEX
    Explanations

    settings locations in different cities or time periods

    oai_token-act-pair · gpt-3.5-turbo

    contexts related to settings or locations in stories or films

    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
    pkg
    -0.78
     Flavoring
    -0.78
    atts
    -0.71
    alys
    -0.69
     resists
    -0.68
     patience
    -0.68
    drivers
    -0.66
    ticket
    -0.66
    ItemTracker
    -0.66
    Spot
    -0.66
    POSITIVE LOGITS
     dystopian
    1.39
     dystop
    1.24
     fictional
    1.12
     futuristic
    1.08
     backdrop
    1.02
     Era
    1.02
     feudal
    0.98
     1950
    0.98
     1920
    0.95
     1940
    0.93
    Activations Density 0.274%

    No Known Activations