© 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. 9209
    Prev
    Next
    INDEX
    Explanations

    words related to genetic mutations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to genetic mutations and their effects

    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
    ħĭ
    -0.86
    taboola
    -0.80
    ¥µ
    -0.77
     Aires
    -0.76
    ¾
    -0.75
    ľ
    -0.74
    eger
    -0.73
    english
    -0.73
    ¬¼
    -0.73
    travel
    -0.73
    POSITIVE LOGITS
     mutation
    1.29
     mutations
    1.17
     allele
    1.02
     mutants
    0.99
     predis
    0.97
     genes
    0.88
     mutated
    0.88
    ulously
    0.87
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.87
     mutant
    0.86
    Activations Density 0.029%

    No Known Activations