© 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. 3612
    Prev
    Next
    INDEX
    Explanations

    words related to ecological concepts and practices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ecological concepts and environmental issues

    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
    MENTS
    -0.86
    ++++++++++++++++
    -0.78
    downs
    -0.77
     Twain
    -0.75
    mast
    -0.73
     Sherlock
    -0.72
    LESS
    -0.71
     Colt
    -0.69
    Magikarp
    -0.69
    Haunted
    -0.68
    POSITIVE LOGITS
    stasy
    1.53
    uador
    1.23
    lectic
    1.05
    umen
    0.96
    uthor
    0.92
    ury
    0.92
    eger
    0.91
    yssey
    0.91
    ologically
    0.91
    ogl
    0.90
    Activations Density 0.012%

    No Known Activations