INDEX

Explanations

terms associated with placement and positioning

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

MultipartFile

-0.76

 مشين

-0.67

__(/*!

-0.65

argout

-0.65

IndentedString

-0.64

MigrationBuilder

-0.62

]<<"

-0.62

Aholisi

-0.62

protoimpl

-0.62

 '\\;'

-0.62

POSITIVE LOGITS

 placement

1.73

 location

1.60

 arrangement

1.59

 positioned

1.58

 Placement

1.55

 located

1.55

 positioning

1.49

Placement

1.49

 position

1.47

located

1.47

Activations Density 2.863%

terms associated with placement and positioning

No Comments

No Known Activations