© 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. 8-RES-JB
    11. 8676
    Prev
    Next
    INDEX
    Explanations

    phrases related to business organizations, specifically chambers of commerce

    oai_token-act-pair · gpt-3.5-turbo

    references to chambers of commerce or similar organizational bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.64
     canal
    -0.60
     foremost
    -0.60
     strand
    -0.60
     abundantly
    -0.59
    fters
    -0.59
    isite
    -0.57
     phosphate
    -0.55
    oward
    -0.55
    ön
    -0.54
    POSITIVE LOGITS
    Õ
    0.81
    DAQ
    0.78
    ð
    0.75
    FACE
    0.68
    ADRA
    0.66
    ãģ¦
    0.65
     Contents
    0.64
    Alert
    0.64
    é£
    0.64
     Savings
    0.63
    Activations Density 0.203%

    No Known Activations