© 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. 10-RES-JB
    11. 12720
    Prev
    Next
    INDEX
    Explanations

    words related to biology and the concept of life

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of life and its various aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DCS
    -0.74
     stra
    -0.73
    rette
    -0.69
    nee
    -0.69
    agger
    -0.64
     Buckingham
    -0.64
     Stra
    -0.64
     Straight
    -0.64
     Hero
    -0.63
    raine
    -0.62
    POSITIVE LOGITS
    forms
    1.33
     organisms
    1.26
     forms
    1.02
     organism
    1.00
    organisms
    0.95
     species
    0.92
    brates
    0.91
     arisen
    0.90
     microbes
    0.89
     inhab
    0.89
    Activations Density 0.050%

    No Known Activations