© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 15550
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that describe a person or thing as being highly regarded or considered among the best in a specific field

    oai_token-act-pair · gpt-3.5-turbo

    phrases that identify individuals or entities as the best or among the best in various fields or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    course
    -0.71
    ierrez
    -0.67
     COURT
    -0.67
    rief
    -0.67
    istries
    -0.62
    Again
    -0.62
    ebook
    -0.59
    interrupted
    -0.58
    umption
    -0.58
    again
    -0.57
    POSITIVE LOGITS
     unbeat
    0.82
     visionary
    0.80
     trustworthy
    0.79
     frontrunner
    0.79
     seminal
    0.78
     genius
    0.76
     superior
    0.75
     pinnacle
    0.75
     groundbreaking
    0.75
     underrated
    0.75
    Activations Density 0.245%

    No Known Activations