© 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. 2-RES-JB
    11. 23647
    Prev
    Next
    INDEX
    Explanations

    references to physical structures like bars

    oai_token-act-pair · gpt-3.5-turbo

    the term "bars" in various contexts, often relating to locations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctive
    -0.96
     GENERAL
    -0.76
    EngineDebug
    -0.75
    åĬ
    -0.74
    ALLY
    -0.72
    EEE
    -0.71
    lihood
    -0.70
    ãĤī
    -0.69
     Commons
    -0.68
    ãģ®å®
    -0.67
    POSITIVE LOGITS
     bars
    1.21
    poon
    1.11
    hops
    1.03
    hop
    0.98
    bars
    0.97
    poons
    0.96
    becue
    0.92
    ingers
    0.92
    manship
    0.92
     Bars
    0.90
    Activations Density 0.010%

    No Known Activations