© 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. 16948
    Prev
    Next
    INDEX
    Explanations

    phrases related to admitting or confessing to something

    oai_token-act-pair · gpt-3.5-turbo

    instances of admissions or confessions related to various actions or crimes

    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
    Liber
    -0.78
    DragonMagazine
    -0.75
     Mehran
    -0.73
    reshold
    -0.73
    intosh
    -0.70
    atos
    -0.69
    Welcome
    -0.69
    eous
    -0.69
    cair
    -0.69
    soon
    -0.68
    POSITIVE LOGITS
     having
    1.21
     raping
    1.19
     wrongdoing
    1.19
     committing
    1.17
     possessing
    1.17
     owning
    1.15
     murdering
    1.12
     assaulting
    1.11
     abusing
    1.11
     manipulating
    1.11
    Activations Density 0.104%

    No Known Activations