© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    words related to tall structures or buildings, specifically focusing on towers

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "tower."

    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
    ãĤ±
    -0.81
    é»Ĵ
    -0.71
    iotic
    -0.70
    dit
    -0.70
     Lives
    -0.68
     Luther
    -0.66
    ãĤŃ
    -0.64
    âĸ¬âĸ¬
    -0.64
    orie
    -0.63
    aline
    -0.62
    POSITIVE LOGITS
     towers
    1.09
     tower
    1.04
     skysc
    0.98
    tower
    0.95
     Towers
    0.94
     heights
    0.94
     erected
    0.93
    raper
    0.92
     blocks
    0.85
     crane
    0.85
    Activations Density 0.039%

    No Known Activations