© 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. 4-RES-JB
    11. 7367
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology and medical research

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms related to biology and genetics

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

    No Comments

    Negative Logits
    ä¸Ĭ
    -0.71
    ticket
    -0.70
     Franch
    -0.68
    Privacy
    -0.66
    Tickets
    -0.64
    éĹ
    -0.63
    iquette
    -0.63
    Rules
    -0.62
    Jimmy
    -0.62
    Flags
    -0.61
    POSITIVE LOGITS
     biologically
    1.08
     mammalian
    1.02
     genetically
    0.99
     genomic
    0.99
     molecular
    0.98
     biological
    0.98
     genetic
    0.96
     phenotype
    0.96
     âĪ¼
    0.96
     biochemical
    0.95
    Activations Density 1.692%

    No Known Activations