INDEX

Explanations

phrases related to visual comparisons or similarities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Jereo

-0.51

 모두

-0.50

 yoksa

-0.48

 adverbs

-0.47

 potrebné

-0.44

ByPrimaryKey

-0.44

 both

-0.43

auto

-0.42

 zowel

-0.42

্ষ

-0.41

POSITIVE LOGITS

like

0.98

ähn

0.81

esque

0.80

CppMethod

0.80

artige

0.79

 TextStyle

0.75

artigen

0.71

LIKE

0.70

styleType

0.69

狀

0.69

Activations Density 0.292%

phrases related to visual comparisons or similarities

No Comments

No Known Activations