© 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. 3-RES-JB
    11. 12345
    Prev
    Next
    INDEX
    Explanations

    phrases related to genetic concepts and genes

    oai_token-act-pair · gpt-3.5-turbo

    references to genes and their related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dragonbound
    -0.77
     Huss
    -0.72
     Christy
    -0.72
    Hour
    -0.72
    ©¶æ¥µ
    -0.71
     Springs
    -0.70
    Laun
    -0.68
     Colleges
    -0.67
    ango
    -0.66
    ij士
    -0.65
    POSITIVE LOGITS
    alogy
    1.40
     gene
    1.13
     genes
    1.12
    etically
    1.04
    alog
    1.04
    etics
    0.98
     mutation
    0.91
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.88
     sequencing
    0.87
     predis
    0.85
    Activations Density 0.014%

    No Known Activations