© 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. 17764
    Prev
    Next
    INDEX
    Explanations

    words related to different sectors such as medical, educational, transportation, entertainment, and community, along with descriptions of events and activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to injury, medical conditions, and emergency situations

    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
    agame
    -0.78
    aminer
    -0.72
    undrum
    -0.69
    mma
    -0.69
     ¯
    -0.67
    ouf
    -0.66
    hyde
    -0.66
    ulet
    -0.64
     Yesterday
    -0.63
    agonist
    -0.62
    POSITIVE LOGITS
     versions
    1.12
     equivalents
    1.02
     replacements
    0.97
     panels
    0.95
     banners
    0.91
     billboards
    0.90
     clauses
    0.89
     variants
    0.89
     agreements
    0.89
     extensions
    0.88
    Activations Density 0.812%

    No Known Activations