© 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. 804
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms related to debt, GDP, and financial indicators

    oai_token-act-pair · gpt-3.5-turbo

    financial indicators and metrics related to economic performance

    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
    odox
    -0.86
    ĪĴ
    -0.83
    Ħ¢
    -0.77
    sonian
    -0.75
    lear
    -0.65
    bay
    -0.64
     mur
    -0.64
    hett
    -0.63
    elight
    -0.63
    otin
    -0.63
    POSITIVE LOGITS
     (%
    1.06
     ($)
    1.03
     totaled
    1.02
     minus
    0.96
     Percentage
    0.93
     ratio
    0.92
     (%)
    0.90
     Ratio
    0.89
     per
    0.88
     total
    0.87
    Activations Density 0.344%

    No Known Activations