© 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. 7291
    Prev
    Next
    INDEX
    Explanations

    business-related entities like studios, publishers, candidates, countries, teams, schools, journals, companies, nations, industrialized countries, and committees

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and categories, particularly those involving groups and classifications

    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
    vik
    -0.75
    entimes
    -0.73
    pmwiki
    -0.70
    erb
    -0.70
    DERR
    -0.67
    biz
    -0.66
    enture
    -0.64
    utters
    -0.64
    growth
    -0.63
    nce
    -0.62
    POSITIVE LOGITS
     listed
    1.15
     vying
    1.02
     finalists
    1.01
     mentioned
    1.01
     respectively
    1.00
     composing
    0.98
     combined
    0.98
     viz
    0.96
     surveyed
    0.95
     simultaneously
    0.92
    Activations Density 0.303%

    No Known Activations