INDEX

Explanations

phrases and terms related to ratings and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endphp

-0.73

knecht

-0.72

 whiteColor

-0.72

'}}>

-0.70

berdayakan

-0.70

 Witte

-0.67

 getRule

-0.67

 Stroh

-0.66

"}}>

-0.65

<>

-0.65

POSITIVE LOGITS

 rating

1.55

 ratings

1.55

 Rating

1.49

 Ratings

1.46

 RATING

1.25

rating

1.23

ratings

1.23

Rating

1.22

Ratings

1.18

 rated

1.01

Activations Density 0.089%

phrases and terms related to ratings and evaluations

No Comments

No Known Activations