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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3340
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sprigg"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Spr" or variations associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.84
    opsy
    -0.76
    ographed
    -0.76
    ographers
    -0.70
    ographer
    -0.67
    raviolet
    -0.65
    ccording
    -0.65
    ocene
    -0.64
    onyms
    -0.64
    rament
    -0.63
    POSITIVE LOGITS
     Spr
    1.09
    inkle
    0.96
    Spr
    0.91
     Canaver
    0.90
    ength
    0.79
    spr
    0.78
    atche
    0.77
    è
    0.73
    ague
    0.72
    endon
    0.72
    Activations Density 0.009%

    No Known Activations