© 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. 2582
    Prev
    Next
    INDEX
    Explanations

    sequences or terms related to genetic sequencing and DNA mutations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to genetic variation and sequencing technologies

    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
    ¥µ
    -0.90
    ħĭ
    -0.86
    taboola
    -0.84
    udeb
    -0.82
    Nap
    -0.81
    ĪĴ
    -0.81
    bilt
    -0.79
    lehem
    -0.78
    Ń·
    -0.75
    ä¸Ĭ
    -0.73
    POSITIVE LOGITS
     genes
    1.30
     DNA
    1.26
     gene
    1.24
     genomes
    1.19
     genomic
    1.16
     genome
    1.14
     embryos
    1.13
     chromosomes
    1.13
     organisms
    1.11
     RNA
    1.10
    Activations Density 0.078%

    No Known Activations