© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and experiments on animals such as mice

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical research and findings involving cellular analysis

    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
    illions
    -0.80
    cair
    -0.78
    ooks
    -0.78
    esta
    -0.77
    hello
    -0.74
    Things
    -0.71
    Story
    -0.70
    iquette
    -0.70
    ById
    -0.70
    stories
    -0.70
    POSITIVE LOGITS
     assay
    1.10
     PCR
    1.01
     genomic
    0.90
     cyt
    0.89
     blinded
    0.87
     analyzed
    0.87
     β
    0.86
    alyses
    0.85
     assessed
    0.85
     (âĪĴ
    0.85
    Activations Density 0.459%

    No Known Activations