INDEX

Explanations

quantitative data represented in ranges or intervals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.59

 mondiale

-0.57

UserScript

-0.56

GraphicsUnit

-0.54

GRANTED

-0.48

Хьажоргаш

-0.48

brainly

-0.46

whole

-0.45

 تضيفلها

-0.45

何も

-0.44

POSITIVE LOGITS

 ujednoznacz

0.78

awtextra

0.70

tocks

0.65

 depending

0.64

Története

0.63

züglich

0.63

anmoins

0.59

 BoxFit

0.57

âtre

0.57

derry

0.57

Activations Density 0.331%

quantitative data represented in ranges or intervals

No Comments

No Known Activations