INDEX

Explanations

code block delimiters

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

évaluateur

-0.97

存于互联网档案馆

-0.95

 itſelf

-0.88

OGND

-0.88

:✨

-0.88

AddTagHelper

-0.88

 autorytatywna

-0.88

MigrationBuilder

-0.85

 bezeichneter

-0.85

Efq

-0.84

POSITIVE LOGITS

 else

1.41

else

1.25

否则

0.83

 otherwise

0.82

 Otherwise

0.76

↵

0.74

 ELSE

0.72

Otherwise

0.70

 other

0.68

 иначе

0.66

Activations Density 0.062%

code block delimiters

No Comments

No Known Activations