© 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. 12575
    Prev
    Next
    INDEX
    Explanations

    terms related to conservation efforts and organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conservation and environmental protection

    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
    ĻĤ
    -0.83
    arb
    -0.71
     redemption
    -0.68
    aciously
    -0.68
    reed
    -0.67
     perjury
    -0.66
     righteous
    -0.65
    olson
    -0.65
    ãĢı
    -0.65
     evident
    -0.65
    POSITIVE LOGITS
     Facilities
    1.16
     Services
    1.10
     Connection
    1.09
     Room
    1.08
     Facility
    1.07
     Sites
    1.07
     Blocks
    1.06
     Rooms
    1.05
     Disorders
    1.04
     Areas
    1.03
    Activations Density 0.087%

    No Known Activations