© 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. 10-RES-JB
    11. 11617
    Prev
    Next
    INDEX
    Explanations

    sentences related to contracts or agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to contract negotiations or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evil
    -0.70
    MpServer
    -0.68
    sylv
    -0.65
     Readers
    -0.64
    otle
    -0.63
     correction
    -0.62
     debunk
    -0.62
    ĸļ
    -0.62
     satir
    -0.61
     amplification
    -0.61
    POSITIVE LOGITS
     contract
    1.14
     contractual
    1.11
     renegoti
    1.08
    signed
    1.05
     signed
    1.05
     waived
    1.03
     waive
    1.01
     waivers
    1.00
     audition
    0.99
     rehab
    0.98
    Activations Density 0.521%

    No Known Activations