© 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. 7325
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific books or publications

    oai_token-act-pair · gpt-3.5-turbo

    references to the Book of Mormon and associated themes

    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
    kaya
    -0.81
    ahime
    -0.80
    etsk
    -0.76
    aterasu
    -0.74
    vous
    -0.67
    kov
    -0.65
    oppable
    -0.65
     Pradesh
    -0.64
    chenko
    -0.64
    utterstock
    -0.63
    POSITIVE LOGITS
     autobiography
    0.85
     memoir
    0.84
     archives
    0.79
    ophon
    0.79
     books
    0.77
     journals
    0.77
     Circus
    0.76
     Books
    0.74
     scrolls
    0.74
     manuals
    0.71
    Activations Density 0.584%

    No Known Activations