INDEX

Explanations

expressions of personal opinion and experiences

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

 Çünkü

-0.72

 çünkü

-0.65

 totiž

-0.65

 entanto

-0.60

 fordi

-0.60

ugy

-0.60

 because

-0.59

因为

-0.59

Denn

-0.59

because

-0.59

POSITIVE LOGITS

จึง

1.24

 naturally

1.02

 forcément

0.88

 accordingly

0.87

 naturellement

0.86

 correspondingly

0.86

Naturally

0.86

也就

0.84

naturally

0.83

 Naturally

0.83

Activations Density 0.527%

expressions of personal opinion and experiences

No Comments

No Known Activations