© 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. 13540
    Prev
    Next
    INDEX
    Explanations

    negative or problematic situations and occurrences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of personal experiences and anecdotes

    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
     Gutenberg
    -0.78
     guiIcon
    -0.76
     enshr
    -0.69
     Haram
    -0.67
    bones
    -0.66
    âĢij
    -0.66
     Abstract
    -0.63
     Presents
    -0.63
     Symbol
    -0.62
    DragonMagazine
    -0.61
    POSITIVE LOGITS
     experien
    1.05
     anecd
    1.04
    Rated
    1.03
     testers
    0.93
     tested
    0.91
     myself
    0.84
     firsthand
    0.84
     mine
    0.84
     experience
    0.84
    exper
    0.83
    Activations Density 1.488%

    No Known Activations