INDEX

Explanations

instances of strong opinions and rhetorical questioning in a debate or discussion context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

روابط

-0.72

னர்

-0.66

letar

-0.52

Portail

-0.52

Kirche

-0.51

 respectivamente

-0.51

لينا

-0.51

AccessorTable

-0.50

Statistiche

-0.50

urman

-0.49

POSITIVE LOGITS

it

0.81

 they

0.66

AndEndTag

0.61

それは

0.55

 Wikispecies

0.55

its

0.50

 surely

0.50

 оно

0.49

 then

0.47

 ujednoznacz

0.47

Activations Density 0.375%

instances of strong opinions and rhetorical questioning in a debate or discussion context

No Comments

No Known Activations