© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4844
    Prev
    Next
    INDEX
    Explanations

    terms related to engraving, etching, and imprinting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of engraving or marking

    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
    DragonMagazine
    -1.01
    Pod
    -0.76
    VICE
    -0.75
    STAR
    -0.73
     GEAR
    -0.72
    phia
    -0.71
    yip
    -0.68
    Universal
    -0.67
    tera
    -0.67
    âķIJ
    -0.67
    POSITIVE LOGITS
     eng
    1.08
    rafted
    0.99
    ravings
    0.89
    rained
    0.87
     wrinkles
    0.86
    raft
    0.83
    raved
    0.81
    join
    0.79
    izzard
    0.79
    amed
    0.78
    Activations Density 0.014%

    No Known Activations