© 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 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. 14706
    Prev
    Next
    INDEX
    Explanations

    terms related to social media hashtags and online contests

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to entertainment and events that involve competition or performance

    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
     Instr
    -0.82
     Fiscal
    -0.79
    Footnote
    -0.79
    Contents
    -0.76
     Osw
    -0.75
    umerable
    -0.74
    STDOUT
    -0.73
    ×ŀ
    -0.72
    Import
    -0.72
     Palest
    -0.72
    POSITIVE LOGITS
     sucks
    1.02
     americ
    0.97
     pics
    0.92
     lol
    0.90
     fallacy
    0.90
     doesnt
    0.88
     dont
    0.87
    !!!!
    0.86
     syndrome
    0.86
     goddess
    0.85
    Activations Density 0.705%

    No Known Activations