INDEX

Explanations

references to meals, particularly lunch

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

 Gilles

-0.65

 knob

-0.65

PropertyGroup

-0.64

Sk

-0.64

Marek

-0.64

Koh

-0.64

følgelig

-0.63

Koh

-0.63

 ThemeData

-0.62

 Tribe

-0.62

POSITIVE LOGITS

 lunch

2.31

 Lunch

2.21

Lunch

2.15

 LUNCH

2.10

lunch

2.01

 lunches

1.90

 luncheon

1.61

 lunchtime

1.56

 Luncheon

1.34

午餐

1.28

Activations Density 0.064%

references to meals, particularly lunch

No Comments

No Known Activations