Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3690
    Prev
    Next
    INDEX
    Explanations

    words related to genetics and gene expression

    oai_token-act-pair · gpt-3.5-turbo

    references to genes and genetic influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dragonbound
    -0.89
     Christy
    -0.75
    ij士
    -0.73
    Hour
    -0.68
    Bull
    -0.66
    Laun
    -0.65
     Springs
    -0.64
    laun
    -0.64
    ©¶æ¥µ
    -0.63
    alach
    -0.61
    POSITIVE LOGITS
    alogy
    1.27
     genes
    1.22
     gene
    1.03
    etically
    1.00
    etics
    0.96
     predis
    0.91
    alog
    0.90
    ogens
    0.82
     molecule
    0.82
     sequencing
    0.80
    Activations Density 0.008%

    No Known Activations