© 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. 12048
    Prev
    Next
    INDEX
    Explanations

    references to financial terms and investment-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to life events and transitions

    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
     rampant
    -0.69
     resent
    -0.64
     tens
    -0.63
     tacit
    -0.62
     caus
    -0.62
     nort
    -0.61
     periphery
    -0.61
     supposedly
    -0.59
     bolster
    -0.59
     dotted
    -0.59
    POSITIVE LOGITS
     Advice
    1.26
     Therapy
    1.18
     Dating
    1.16
     Training
    1.15
     Functions
    1.14
     Moves
    1.14
     Examination
    1.14
     Recipes
    1.14
     Rates
    1.14
     Techniques
    1.13
    Activations Density 0.684%

    No Known Activations