© 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. 20804
    Prev
    Next
    INDEX
    Explanations

    economic and statistical terms related to projections or expectations

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to price predictions and expectations in various markets

    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
     elig
    -0.74
    arthed
    -0.72
    sonian
    -0.69
    ovie
    -0.65
    assian
    -0.65
     paran
    -0.63
     Printed
    -0.61
     Wast
    -0.61
    asking
    -0.59
     pregnant
    -0.59
    POSITIVE LOGITS
     soar
    1.51
     plummet
    1.40
     skyrocket
    1.40
     rise
    1.38
     decrease
    1.27
     stabilize
    1.26
     surge
    1.26
     increase
    1.25
     decline
    1.25
     spike
    1.23
    Activations Density 0.109%

    No Known Activations