INDEX

Explanations

names of languages and geographical locations

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

 fica

-0.44

 alerg

-0.43

 device

-0.43

Utf

-0.41

 backless

-0.40

 lank

-0.40

Idaho

-0.40

 ukra

-0.39

Oregon

-0.39

 Balkans

-0.39

POSITIVE LOGITS

+#+#

0.72

клопе

0.67

zzleHttp

0.66

 Normdatei

0.65

NT

0.64

ніципа

0.64

erapeutics

0.63

发表于

0.63

 Katherine

0.62

Aru

0.61

Activations Density 0.099%

names of languages and geographical locations

No Comments

No Known Activations