© 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. 11-RES-JB
    11. 6822
    Prev
    Next
    INDEX
    Explanations

    technical terms related to medical research and genetic manipulation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to biological research and therapy techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gencies
    -0.85
     Ranking
    -0.80
     Timber
    -0.78
     Occupations
    -0.77
    Ń·
    -0.76
    Chart
    -0.75
    ibliography
    -0.72
    asonry
    -0.71
    âĢİ
    -0.71
     Chart
    -0.71
    POSITIVE LOGITS
     mice
    1.40
     embryos
    1.39
     nanop
    1.36
     genetically
    1.35
    RNA
    1.34
     cultured
    1.33
     RNA
    1.29
     implanted
    1.28
     engineered
    1.27
     injected
    1.25
    Activations Density 0.336%

    No Known Activations