© 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. 0-RES-JB
    11. 4966
    Prev
    Next
    INDEX
    Explanations

    words related to strong defense or protection

    oai_token-act-pair · gpt-3.5-turbo

    references to fortifications and defensive structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HL
    -0.79
     Bloom
    -0.79
    ociation
    -0.74
     Lumpur
    -0.72
     Results
    -0.71
     Review
    -0.71
     Online
    -0.71
    Asian
    -0.71
    Online
    -0.71
     Paid
    -0.70
    POSITIVE LOGITS
     fort
    3.83
     fortified
    1.81
     fortress
    1.73
     barric
    1.35
     garrison
    1.23
    fort
    1.21
     besie
    1.13
     bunker
    1.13
     castles
    1.12
     castle
    1.09
    Activations Density 0.017%

    No Known Activations