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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 20268
    Prev
    Next
    INDEX
    Explanations

    phrases related to cell biology and medical research, specifically focusing on cellular activities and stem cell manipulation

    oai_token-act-pair · gpt-3.5-turbo

    scientific terminology related to cell cultures and blood formation

    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
    leans
    -0.92
    Weather
    -0.83
    aution
    -0.78
    anship
    -0.77
    imity
    -0.76
     Skies
    -0.75
     Economics
    -0.74
    âĺħâĺħ
    -0.71
    soDeliveryDate
    -0.70
    iquette
    -0.70
    POSITIVE LOGITS
     cells
    1.67
    ocytes
    1.57
     Cells
    1.40
    cells
    1.37
     embryos
    1.36
     embryonic
    1.33
     neurons
    1.32
     mitochond
    1.32
     chromosomes
    1.27
     stem
    1.26
    Activations Density 0.256%

    No Known Activations