INDEX

Explanations

terms related to zooming and panning in visual contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addCriterion

-0.70

BeginContext

-0.67

WriteTagHelper

-0.60

}]

-0.59

 didReceive

-0.58

CardContent

-0.58

setHeader

-0.57

exitRule

-0.57

wts

-0.57

awtextra

-0.57

POSITIVE LOGITS

 zoom

2.27

Zoom

2.18

 Zoom

2.15

zoom

2.07

 ZOOM

2.06

ZOOM

1.85

 zoomed

1.59

 zooming

1.59

 zoon

1.05

Zo

0.99

Activations Density 0.088%

terms related to zooming and panning in visual contexts

No Comments

No Known Activations