© 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. 4-RES-JB
    11. 1977
    Prev
    Next
    INDEX
    Explanations

    references to air conditioning units

    oai_token-act-pair · gpt-3.5-turbo

    references to air conditioning

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

    No Comments

    Negative Logits
    doms
    -0.78
     Fenrir
    -0.75
     Tradable
    -0.75
    cake
    -0.71
    jar
    -0.68
    ozyg
    -0.68
    ãĥĦ
    -0.67
    vous
    -0.67
    ãĥĭ
    -0.65
    heimer
    -0.65
    POSITIVE LOGITS
    oust
    0.97
    rylic
    0.94
    oustic
    0.93
    ORN
    0.90
    ros
    0.86
     metic
    0.85
    CEPT
    0.81
    RIC
    0.81
    robat
    0.80
    upuncture
    0.80
    Activations Density 0.005%

    No Known Activations