© 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. 6-RES-JB
    11. 13448
    Prev
    Next
    INDEX
    Explanations

    words related to basic necessities or essentials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to essentials and necessities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.85
    ongyang
    -0.82
    lex
    -0.75
    raid
    -0.74
    appa
    -0.73
    asus
    -0.71
    ramid
    -0.70
    lez
    -0.70
    obar
    -0.69
    onel
    -0.68
    POSITIVE LOGITS
     namely
    0.87
    hooting
    0.83
     goodies
    0.77
     ashore
    0.76
     essentials
    0.74
    ãģĨ
    0.74
     abound
    0.73
     gal
    0.73
     pertaining
    0.72
    mith
    0.71
    Activations Density 0.131%

    No Known Activations