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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6791
    Prev
    Next
    INDEX
    Explanations

    words related to organisms

    oai_token-act-pair · gpt-3.5-turbo

    references to living organisms and their relationships within ecosystems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.73
    ership
    -0.73
    ãĥ¼ãĥ³
    -0.72
    ãĥ´ãĤ¡
    -0.70
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.63
    Ku
    -0.63
    heed
    -0.63
    nder
    -0.62
    ndra
    -0.62
    awar
    -0.61
    POSITIVE LOGITS
     organisms
    1.22
     organism
    1.16
    cules
    0.87
     spores
    0.86
    brates
    0.86
    acteria
    0.85
     worms
    0.85
     symb
    0.81
     microbes
    0.81
     bacteria
    0.80
    Activations Density 0.018%

    No Known Activations