© 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. 11-RES-JB
    11. 4845
    Prev
    Next
    INDEX
    Explanations

    mentions of financial debt or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to debt and financial obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.91
    Ļ½
    -0.74
    laus
    -0.72
    getic
    -0.70
    irus
    -0.69
     Klu
    -0.67
    Ùĩ
    -0.67
    anism
    -0.65
    zbek
    -0.65
    £ı
    -0.63
    POSITIVE LOGITS
     repayment
    1.29
     repay
    1.14
     incurred
    1.11
     forgiveness
    1.10
     ceiling
    1.07
    ors
    1.06
     owed
    1.02
     burdens
    1.00
     bondage
    1.00
     servicing
    0.99
    Activations Density 0.047%

    No Known Activations