INDEX

Explanations

parameters related to image and figure dimensions in a document

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

LookAnd

-1.06

IsMutable

-1.05

OGND

-1.02

setVerticalGroup

-0.99

StructEnd

-0.96

IndentedString

-0.96

ThroughAttribute

-0.93

 Roskov

-0.93

 nahilalakip

-0.92

AsUp

-0.91

POSITIVE LOGITS

 width

0.81

 size

0.62

 Width

0.58

 шири

0.56

width

0.56

 taille

0.50

 bounds

0.49

 widths

0.48

 размеры

0.47

 ширина

0.47

Activations Density 0.041%

parameters related to image and figure dimensions in a document

No Comments

No Known Activations