© 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. 4-RES-JB
    11. 19770
    Prev
    Next
    INDEX
    Explanations

    phrases related to adoption or adoption-like actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to adoption and interpretation

    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
     Toast
    -0.72
     toast
    -0.68
     Pillar
    -0.67
    beard
    -0.66
    hands
    -0.65
     Shades
    -0.65
     Shakespeare
    -0.63
     Divinity
    -0.63
     Everest
    -0.61
     Panic
    -0.61
    POSITIVE LOGITS
    itors
    1.03
    itives
    1.01
    nation
    0.98
    ues
    0.97
    eties
    0.96
    acy
    0.95
    Ĭ
    0.94
    eness
    0.94
    icion
    0.94
    itive
    0.91
    Activations Density 0.022%

    No Known Activations