INDEX

Explanations

references to knowledge and familiarity with people or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

üman

-0.57

 into

-0.57

addContainerGap

-0.49

kháu

-0.47

 словарь

-0.46

tagHelperRunner

-0.45

 Into

-0.43

 stalo

-0.43

cyjny

-0.42

rzost

-0.42

POSITIVE LOGITS

 intimately

1.13

 well

1.09

 better

0.93

 dobrze

0.92

 جيد

0.91

 dobře

0.85

 doskon

0.81

 WELL

0.80

better

0.80

 Bescheid

0.79

Activations Density 0.142%

references to knowledge and familiarity with people or places

No Comments

No Known Activations