INDEX

Explanations

references to Norway

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

 useEffect

-0.65

 repens

-0.60

 propOrder

-0.58

 limpio

-0.57

cambrian

-0.56

 árabe

-0.56

 rechange

-0.55

 Cientí

-0.54

Œuvres

-0.54

AccessException

-0.53

POSITIVE LOGITS

Nor

0.85

Nor

0.84

 Nore

0.79

NOR

0.69

 Norris

0.67

͘

0.64

 norms

0.62

awtextra

0.59

therners

0.58

 Nors

0.58

Activations Density 0.113%

references to Norway

No Comments

No Known Activations