© 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. 4-RES-JB
    11. 16630
    Prev
    Next
    INDEX
    Explanations

    names and variations of the name "Rad"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.74
    urities
    -0.73
    ãĥīãĥ©
    -0.70
    redits
    -0.69
    FAULT
    -0.67
    ORTS
    -0.66
    pload
    -0.65
    terday
    -0.64
     Countdown
    -0.64
    veyard
    -0.64
    POSITIVE LOGITS
    iance
    1.19
    iated
    1.09
    iation
    1.07
    iate
    1.05
    ient
    1.03
    isson
    1.01
    iations
    0.97
    iant
    0.96
    ios
    0.93
    iop
    0.92
    Activations Density 0.011%

    No Known Activations