© 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. 3-RES-JB
    11. 20334
    Prev
    Next
    INDEX
    Explanations

    references to the presence or absence of oxygen in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of oxygen and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.90
    invoke
    -0.73
    enegger
    -0.72
    ORN
    -0.72
     Judgment
    -0.71
    erers
    -0.69
    HCR
    -0.69
    ochet
    -0.68
    2019
    -0.67
    things
    -0.67
    POSITIVE LOGITS
     oxygen
    1.08
     isot
    0.93
     dioxide
    0.93
     oxide
    0.90
     molecule
    0.87
     saline
    0.87
     nitrogen
    0.83
     saturation
    0.82
     molecules
    0.80
    oglobin
    0.79
    Activations Density 0.010%

    No Known Activations