© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 9040
    Prev
    Next
    INDEX
    Explanations

    references to underground locations or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to underground locations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awed
    -0.81
    ointed
    -0.79
    cific
    -0.79
    neapolis
    -0.75
    ettle
    -0.74
    Äĩ
    -0.72
    bourg
    -0.72
    abeth
    -0.72
    ño
    -0.71
    pered
    -0.71
    POSITIVE LOGITS
     Railroad
    0.98
    ranean
    0.93
     Bunker
    0.92
     bunker
    0.90
     labyrinth
    0.88
     railroad
    0.88
     tunnels
    0.86
     cavern
    0.86
     workings
    0.85
     lair
    0.85
    Activations Density 0.035%

    No Known Activations