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

    Neuronpedia

    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. 17475
    Prev
    Next
    INDEX
    Explanations

    mentions of environmentally friendly or unfriendly actions or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental concepts and issues

    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
    downs
    -0.82
    channelAvailability
    -0.70
    down
    -0.69
    oons
    -0.69
     Gott
    -0.68
     Hogan
    -0.66
     McGee
    -0.66
    Subject
    -0.65
    ibur
    -0.64
     ILCS
    -0.64
    POSITIVE LOGITS
     eco
    1.15
    femin
    0.91
    entric
    0.82
     sustainability
    0.82
    ë
    0.80
    Boost
    0.77
    friendly
    0.77
    sect
    0.73
    Äį
    0.72
    lect
    0.71
    Activations Density 0.012%

    No Known Activations