© 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. 10-RES-JB
    11. 10036
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns that convey a strong sense of challenging established norms or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate defiance or resistance against norms or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     praying
    -0.72
     dressing
    -0.69
     lug
    -0.69
     donating
    -0.68
     booking
    -0.66
     scra
    -0.65
     withdrawing
    -0.64
     parting
    -0.64
     sweating
    -0.64
     renting
    -0.63
    POSITIVE LOGITS
    uates
    1.17
    ifies
    1.12
    olves
    1.08
    iates
    1.04
    icates
    1.04
    etheless
    1.03
    tains
    1.01
    cludes
    0.98
    ounded
    0.97
    ould
    0.94
    Activations Density 0.165%

    No Known Activations