INDEX

Explanations

references to visual elements and their positions within 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

 stedet

-0.59

 langues

-0.56

 auraient

-0.55

 appartiennent

-0.55

pēc

-0.50

CreateMap

-0.49

 Playhouse

-0.48

"…

-0.48

andExpect

-0.48

 đạo

-0.47

POSITIVE LOGITS

 مشين

0.76

BeginInit

0.66

BeginContext

0.64

ieteur

0.60

EndInit

0.59

PRNewswire

0.57

 sidebar

0.57

 חיצוניים

0.57

addGap

0.56

WriteBarrier

0.56

Activations Density 0.781%

references to visual elements and their positions within a document

No Comments

No Known Activations