INDEX

Explanations

numbers and their associated words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Geplaatst

-0.69

клопе

-0.63

formik

-0.63

 Orrell

-0.62

 WaitForSeconds

-0.59

 mergeFrom

-0.59

IntoConstraints

-0.56

erb

-0.56

WebServlet

-0.56

 onOptions

-0.55

POSITIVE LOGITS

something

0.82

 something

0.74

 percent

0.70

five

0.67

Something

0.65

 thirty

0.63

oned

0.61

 twenty

0.61

two

0.59

 Something

0.59

Activations Density 0.082%

numbers and their associated words

No Comments

No Known Activations