© 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. 20681
    Prev
    Next
    INDEX
    Explanations

    European landmarks, specifically focusing on the Eiffel Tower

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "Eiffel" and related terms

    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
     short
    -0.74
     Nex
    -0.68
     interchangeable
    -0.66
     LIA
    -0.66
     Bliss
    -0.64
     anonymous
    -0.63
     Abbott
    -0.62
    SPONSORED
    -0.62
     phantom
    -0.61
     shortest
    -0.61
    POSITIVE LOGITS
    orst
    1.10
    enth
    1.08
    arden
    1.08
    enberg
    1.07
    orf
    1.06
    acus
    1.05
    acht
    1.05
    ach
    1.04
    itsch
    1.03
    eng
    1.02
    Activations Density 0.118%

    No Known Activations