© 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. 8-RES-JB
    11. 10243
    Prev
    Next
    INDEX
    Explanations

    terms related to economics and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic metrics and costs

    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
    interstitial
    -0.88
    omorphic
    -0.77
    oros
    -0.71
     Cele
    -0.65
    bern
    -0.64
    icians
    -0.63
     fault
    -0.63
    zbek
    -0.62
    ician
    -0.61
    acan
    -0.61
    POSITIVE LOGITS
     considerably
    1.10
     exponentially
    1.04
     dramatically
    1.02
     significantly
    0.95
     tremendously
    0.94
     drastically
    0.94
     substantially
    0.93
     enormously
    0.90
    ahime
    0.86
     accordingly
    0.81
    Activations Density 0.341%

    No Known Activations