© 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. 24043
    Prev
    Next
    INDEX
    Explanations

    words related to green color

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the concept of "green" or environmentally friendly practices

    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
     CNS
    -0.65
    tor
    -0.63
    NRS
    -0.62
    FAULT
    -0.62
    EMP
    -0.62
    ISO
    -0.61
     CPC
    -0.60
    BIP
    -0.60
    WD
    -0.59
    WM
    -0.59
    POSITIVE LOGITS
    igans
    1.15
    reen
    1.04
    issance
    0.99
    vironment
    0.99
    oing
    0.85
    atives
    0.84
    ergic
    0.83
    osuke
    0.82
    igan
    0.80
    eem
    0.80
    Activations Density 0.009%

    No Known Activations