© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 7579
    Prev
    Next
    INDEX
    Explanations

    terms related to financial default or defaulting on payments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial defaults

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rica
    -0.81
    女
    -0.74
    ando
    -0.73
    uana
    -0.69
    eele
    -0.69
    gae
    -0.68
    ĸļ
    -0.65
     Ern
    -0.63
    andan
    -0.63
    anders
    -0.62
    POSITIVE LOGITS
    ing
    0.80
     debtor
    0.79
    uation
    0.78
    ed
    0.74
     judgment
    0.71
    uating
    0.70
     owed
    0.69
    uates
    0.68
     repayment
    0.67
    action
    0.67
    Activations Density 0.026%

    No Known Activations