© 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. 5000
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of accepting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of acceptance, offers, and petitions

    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
    rast
    -0.64
    ï¸ı
    -0.63
    ochond
    -0.63
    abouts
    -0.61
    visual
    -0.60
    acco
    -0.59
    ggles
    -0.59
     Alley
    -0.59
    ionage
    -0.58
     glands
    -0.58
    POSITIVE LOGITS
     invitation
    1.26
     invitations
    1.02
     offer
    0.98
     responsibility
    0.96
     apology
    0.91
     offers
    0.90
     resignation
    0.87
    offer
    0.86
     uncond
    0.86
     advances
    0.86
    Activations Density 0.156%

    No Known Activations