© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10382
    Prev
    Next
    INDEX
    Explanations

    terms related to poetry and poetic language

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "popular" or "mainstream" culture

    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
    soever
    -0.77
    rals
    -0.68
     EntityItem
    -0.66
     embodiments
    -0.66
    pring
    -0.64
     CLIENT
    -0.63
    Interstitial
    -0.63
    croft
    -0.62
     Sherman
    -0.62
     Empires
    -0.62
    POSITIVE LOGITS
    pper
    1.30
    ppy
    1.19
    pping
    1.16
    pped
    1.09
    oldown
    1.03
    ppel
    1.03
    vernment
    1.02
    zzo
    1.00
    cean
    0.98
    onga
    0.96
    Activations Density 0.011%

    No Known Activations