© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23199
    Prev
    Next
    INDEX
    Explanations

    specific mentions of monuments or references to monuments

    oai_token-act-pair · gpt-3.5-turbo

    references to monuments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EAR
    -0.78
    OTT
    -0.75
    FP
    -0.75
    BILITIES
    -0.73
    OTS
    -0.72
     Klu
    -0.68
    ml
    -0.68
    FO
    -0.67
    tails
    -0.67
    ilk
    -0.67
    POSITIVE LOGITS
     monument
    1.34
     monuments
    1.26
     skelet
    0.92
     erected
    0.89
    wikipedia
    0.88
     tremend
    0.88
    arium
    0.87
     decoration
    0.86
     Monument
    0.86
    anan
    0.83
    Activations Density 0.009%

    No Known Activations