© 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. 6-RES-JB
    11. 20399
    Prev
    Next
    INDEX
    Explanations

    financial terms related to yields and returns

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "yield" relating to returns or outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemat
    -0.73
    zb
    -0.65
    ovic
    -0.60
    este
    -0.60
    zai
    -0.60
    ̶
    -0.59
    aldo
    -0.59
     finances
    -0.57
     tox
    -0.57
    mal
    -0.57
    POSITIVE LOGITS
     yield
    0.94
     yields
    0.85
    bang
    0.79
     yielding
    0.74
    ensical
    0.73
     curve
    0.72
    ivation
    0.71
    ells
    0.71
    ivated
    0.69
    uces
    0.69
    Activations Density 0.019%

    No Known Activations