INDEX

Explanations

comparative phrases indicating effectiveness and variability of strategies, breeds, or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AndEndTag

-0.80

bootstrapcdn

-0.71

oldo

-0.63

addCriterion

-0.62

 }}"></

-0.62

rawDesc

-0.61

 kaynağından

-0.61

\{\\

-0.61

subpackage

-0.60

³.

-0.59

POSITIVE LOGITS

 better

0.47

 specific

0.47

 Bestimm

0.46

ėj

0.43

 certain

0.42

солю

0.41

 others

0.41

 naturellement

0.41

 more

0.40

specific

0.38

Activations Density 0.201%

comparative phrases indicating effectiveness and variability of strategies, breeds, or options

No Comments

No Known Activations