© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16664
    Prev
    Next
    INDEX
    Explanations

    terms related to economics and financial matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic metrics or indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.59
     thereafter
    -0.52
    Interstitial
    -0.50
     [âĢ¦]
    -0.50
     latter
    -0.48
    anooga
    -0.47
    Otherwise
    -0.45
     afterwards
    -0.44
    itant
    -0.44
    Ö¼
    -0.43
    POSITIVE LOGITS
     Tuls
    0.54
     âĵĺ
    0.47
     Buffett
    0.46
     Schw
    0.46
     Canaver
    0.45
     DeVos
    0.45
     Marijuana
    0.45
     Insp
    0.44
     Rewards
    0.44
     Poc
    0.41
    Activations Density 2.526%

    No Known Activations