INDEX

Explanations

lists of items or features

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

 betweenstory

-1.00

 ModelExpression

-0.90

 мәкал

-0.85

=$?

-0.84

sizeCache

-0.81

 PyLong

-0.81

adaptiveStyles

-0.80

addCriterion

-0.80

脚注の使い方

-0.79

 pinulongan

-0.79

POSITIVE LOGITS

•

1.73

•

1.56

1.33

·

1.25

●

1.24

・

1.24

・

1.24

·

1.24

・

1.19



1.04

Activations Density 0.290%

lists of items or features

No Comments

No Known Activations