© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 144
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "moon"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the substring "oon"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.75
    ersive
    -0.71
    rf
    -0.70
    utic
    -0.68
    ãĤº
    -0.68
     FANT
    -0.66
    rament
    -0.66
    URES
    -0.65
     EFF
    -0.65
     CONC
    -0.63
    POSITIVE LOGITS
    oon
    1.07
    oons
    0.93
    odon
    0.87
    ship
    0.85
    erness
    0.83
    uclear
    0.82
    itored
    0.82
    ishly
    0.81
    eous
    0.79
    heim
    0.79
    Activations Density 0.010%

    No Known Activations