© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16428
    Prev
    Next
    INDEX
    Explanations

    mentions of biological cells, particularly stem cells, and their characteristics/activity

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AUD
    -0.77
    âĺħâĺħ
    -0.76
     Mint
    -0.75
     Cowboy
    -0.73
    omore
    -0.65
    ideo
    -0.64
     mascot
    -0.64
    oof
    -0.63
     endorsing
    -0.62
     Pole
    -0.62
    POSITIVE LOGITS
     cells
    3.83
     Cells
    3.16
     cell
    2.59
    cells
    2.55
     Cell
    2.02
    Cell
    1.91
     neurons
    1.90
    ocytes
    1.80
    cell
    1.62
     cellular
    1.47
    Activations Density 0.023%

    No Known Activations