© 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. 2-RES-JB
    11. 12954
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial debts or obligations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with unpaid debts and financial obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erion
    -1.08
    igm
    -0.88
    oppers
    -0.86
    oys
    -0.85
    igmat
    -0.80
    inic
    -0.79
    obar
    -0.76
    rieg
    -0.75
    omach
    -0.74
    ocobo
    -0.73
    POSITIVE LOGITS
     unpaid
    1.39
     dues
    0.77
     minerals
    0.76
     delinquent
    0.75
     overtime
    0.75
     owed
    0.72
     overdue
    0.72
     labor
    0.72
     debts
    0.71
     labour
    0.69
    Activations Density 0.018%

    No Known Activations