© 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. 12460
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names containing the letters "Rad"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Rad" in various contexts

    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
    redits
    -0.76
    ORTS
    -0.75
    pload
    -0.75
    Ń·
    -0.70
     Countdown
    -0.68
    ãĥīãĥ©
    -0.68
    FAULT
    -0.68
    terday
    -0.65
    %]
    -0.63
    shapeshifter
    -0.62
    POSITIVE LOGITS
    iance
    1.17
    ient
    1.03
     Rad
    1.01
    isson
    0.99
    iated
    0.97
    iation
    0.93
    isco
    0.92
    iosyn
    0.92
    iop
    0.91
    iate
    0.90
    Activations Density 0.007%

    No Known Activations