INDEX

Explanations

acknowledgments and support statements in research papers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.63

wür

-0.52

<bos>

-0.50

}}$\\

-0.48

//

-0.47

↵↵

-0.46

↵↵↵

-0.45

 Type

-0.45

OCA

-0.44

POSITIVE LOGITS

StoryboardSegue

0.99

 >=",

0.76

orianCalendar

0.74

WebVitals

0.73

ftagPool

0.70

 AssemblyProduct

0.69

harapkan

0.69

 للمعارف

0.67

WebControls

0.65

님

0.64

Activations Density 0.462%

acknowledgments and support statements in research papers

No Comments

No Known Activations