INDEX

Explanations

references to languages and language-related terms

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

"language" or related terms

np_acts-logits-general · gemini-2.0-flash

language and its usage

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ücks

-0.73

:✨

-0.63

 ErrInvalid

-0.61

isome

-0.60

ſelves

-0.59

 purpoſe

-0.58

 occafion

-0.58

 greateſt

-0.58

 reaſon

-0.58

eroy

-0.58

POSITIVE LOGITS

auge

0.65

0.62

 spoken

0.61

Languages

0.61

 languages

0.61

 Lang

0.61

UAGES

0.59

caffe

0.59

 LANG

0.59

 Language

0.58

Activations Density 0.082%

references to languages and language-related terms

"language" or related terms

language and its usage

No Comments

No Known Activations