© 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. 2-RES-JB
    11. 22011
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Sprigg"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Sprouts" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.89
    ographed
    -0.83
    ographers
    -0.80
    opsy
    -0.78
    otomy
    -0.77
    ographer
    -0.73
    versions
    -0.73
    onyms
    -0.71
    husband
    -0.70
    */(
    -0.69
    POSITIVE LOGITS
    inkle
    0.95
     SPR
    0.91
     Spr
    0.91
    Spr
    0.88
    inters
    0.82
    spr
    0.80
    atche
    0.79
    è
    0.76
    ight
    0.75
    ength
    0.74
    Activations Density 0.006%

    No Known Activations