© 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 EvalsExportsinterp-engineNEWAPI 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. 14284
    Prev
    Next
    INDEX
    Explanations

    economic and statistical terms

    oai_token-act-pair · gpt-3.5-turbo

    contrasts and comparisons in statistical or factual information

    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
    ĸļ
    -0.91
    obyl
    -0.81
    blind
    -0.75
    sonian
    -0.73
    DragonMagazine
    -0.73
    »Ĵ
    -0.72
    bard
    -0.70
    matter
    -0.69
    blank
    -0.69
    umbn
    -0.69
    POSITIVE LOGITS
     GDP
    1.23
     incomes
    1.23
     productivity
    1.19
     declines
    1.18
     median
    1.16
     inflation
    1.16
     growth
    1.15
     prices
    1.15
     rates
    1.13
     revenues
    1.12
    Activations Density 0.295%

    No Known Activations