Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17627
    Prev
    Next
    INDEX
    Explanations

    economic terms and indicators

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic weakness and downturns

    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
     oath
    -0.91
     Torah
    -0.75
     prost
    -0.75
    wiki
    -0.74
     Allaah
    -0.72
     parap
    -0.70
    seless
    -0.69
     Oath
    -0.69
     bigot
    -0.66
    CHAT
    -0.65
    POSITIVE LOGITS
    flation
    1.11
    luster
    1.07
     recession
    1.02
     deflation
    1.00
     depreciation
    0.99
     inflation
    0.96
     bullish
    0.94
    economic
    0.90
     downward
    0.90
     slowdown
    0.87
    Activations Density 0.370%

    No Known Activations