© 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. 11-RES-JB
    11. 22563
    Prev
    Next
    INDEX
    Explanations

    mention of percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    economic metrics and conditions related to inflation and interest rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nsics
    -0.80
     Trojan
    -0.73
     Trophy
    -0.69
    roups
    -0.65
     trophies
    -0.65
     Imran
    -0.64
    amera
    -0.64
    VPN
    -0.63
     NCT
    -0.63
     lingu
    -0.63
    POSITIVE LOGITS
     inflation
    1.35
     CPI
    1.31
    flation
    1.20
     volatility
    1.10
     deflation
    1.05
     coupon
    1.00
     interest
    0.98
     depreciation
    0.96
     indexed
    0.95
     Mortgage
    0.94
    Activations Density 0.280%

    No Known Activations