© 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. 4-RES-JB
    11. 118
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Spr" or "Sprinkle"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Spr" and its variations

    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
    culosis
    -0.76
    sighted
    -0.70
    ographed
    -0.70
    */(
    -0.68
    ographers
    -0.68
     managerial
    -0.66
    ographer
    -0.64
    ctica
    -0.64
     gestation
    -0.64
    opsy
    -0.63
    POSITIVE LOGITS
    inkle
    1.04
    atche
    0.95
    inters
    0.87
    ight
    0.87
    spr
    0.87
    Spr
    0.86
    inger
    0.86
    itzer
    0.85
    ength
    0.85
    endon
    0.82
    Activations Density 0.006%

    No Known Activations