© 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. 2-RES-JB
    11. 22413
    Prev
    Next
    INDEX
    Explanations

    numerical values typically related to financial situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "yield," particularly in financial or production contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemat
    -0.73
    ovie
    -0.70
     scapego
    -0.69
    olog
    -0.69
    ̶
    -0.68
    oan
    -0.67
    alg
    -0.66
    ocal
    -0.64
     compuls
    -0.64
    opal
    -0.63
    POSITIVE LOGITS
     yield
    1.28
     yields
    1.19
     yielding
    1.03
     yielded
    0.84
    icult
    0.77
    ENCY
    0.76
    xual
    0.70
    ensical
    0.70
    Luck
    0.70
    iculty
    0.68
    Activations Density 0.009%

    No Known Activations