© 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. 8-RES-JB
    11. 2261
    Prev
    Next
    INDEX
    Explanations

    information related to monetary amounts and funding received by various entities

    oai_token-act-pair · gpt-3.5-turbo

    references to financial figures and economic investments

    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
    few
    -0.84
    »Ĵ
    -0.77
    PASS
    -0.74
    chool
    -0.72
    deck
    -0.72
    dar
    -0.70
    ĸļ
    -0.68
    btn
    -0.68
    emo
    -0.67
    MODE
    -0.67
    POSITIVE LOGITS
     cash
    1.11
     dollars
    1.06
     revenue
    1.05
     excess
    0.98
     total
    0.97
     compensation
    0.95
     subsidies
    0.94
     revenues
    0.94
     expenditures
    0.93
     debt
    0.91
    Activations Density 0.065%

    No Known Activations