INDEX

Explanations

introductory phrases or formal commands related to procedural instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ElementException

-0.72

 snippetHide

-0.71

Enlaces

-0.71

 myſelf

-0.65

رشف

-0.65

hassee

-0.65

 linkovi

-0.65

 Paglinawan

-0.62

 domestique

-0.62

 препратки

-0.61

POSITIVE LOGITS

InvalidProtocol

0.46

UnusedPrivate

0.40

 autorytatywna

0.39

ymal

0.36

.“

0.36

 kezd

0.36

NameInMap

0.35

fa

0.35

 Stars

0.35

Stars

0.35

Activations Density 0.786%

introductory phrases or formal commands related to procedural instructions

No Comments

No Known Activations