INDEX

Explanations

phrases related to health-related products and their purchasing information

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

ValueStyle

-0.93

writeFieldEnd

-0.87

 propOrder

-0.82

tagHelperRunner

-0.80

FormTagHelper

-0.79

extAlignment

-0.78

 GenerationType

-0.78

 ligiloj

-0.76

ponses

-0.75

 tartalomajánló

-0.73

POSITIVE LOGITS

best

0.75

Best

0.70

 best

0.68

how

0.66

 Best

0.65

how

0.64

 aikaa

0.60

 beſt

0.60

 viata

0.55

 potrivit

0.53

Activations Density 0.033%

phrases related to health-related products and their purchasing information

No Comments

No Known Activations