© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17316
    Prev
    Next
    INDEX
    Explanations

    mentions of renewing contracts, memberships, traditions, or relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of renewal or re-establishment

    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
    ahi
    -0.71
    OSS
    -0.65
    ramid
    -0.64
    uchs
    -0.64
     Camel
    -0.63
    pper
    -0.62
    riel
    -0.61
    OTH
    -0.61
    OPS
    -0.60
    hedral
    -0.59
    POSITIVE LOGITS
     renew
    1.27
     renewal
    1.25
     Renew
    0.99
    ables
    0.86
     lease
    0.81
    ital
    0.80
    undown
    0.80
     leases
    0.78
     expiration
    0.76
    ably
    0.76
    Activations Density 0.013%

    No Known Activations