© 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. 3664
    Prev
    Next
    INDEX
    Explanations

    instances of the word "renewed"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "renewed" in various contexts

    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
    ohm
    -0.78
    ahi
    -0.77
    pper
    -0.77
    onne
    -0.74
    BIT
    -0.73
    holes
    -0.72
    uchs
    -0.69
     Hedge
    -0.69
    dor
    -0.68
    RIP
    -0.68
    POSITIVE LOGITS
     renew
    1.13
     renewal
    1.02
     renewed
    0.99
     vig
    0.96
     vitality
    0.95
     confir
    0.92
     impetus
    0.91
     warr
    0.89
     tremend
    0.86
     lease
    0.83
    Activations Density 0.008%

    No Known Activations