© 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. 4-RES-JB
    11. 676
    Prev
    Next
    INDEX
    Explanations

    terms related to paying off debts or achieving positive outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to payoff or financial recompense

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

    No Comments

    Negative Logits
    İĭ
    -0.89
    umn
    -0.86
    Ń·
    -0.72
    ography
    -0.70
    yrinth
    -0.69
     Dull
    -0.68
    ften
    -0.65
    mm
    -0.64
    ocular
    -0.62
    Ĭ±
    -0.62
    POSITIVE LOGITS
     dividends
    0.88
     dues
    0.88
     royalties
    0.84
     kindness
    0.77
     ransom
    0.77
     taxes
    0.71
     bribe
    0.70
     extortion
    0.70
    ainment
    0.69
     installments
    0.67
    Activations Density 0.059%

    No Known Activations