INDEX

Explanations

recommendations for dining experiences or specific food items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

TagMode

-0.80

脚注の使い方

-0.71

تقاوى

-0.68

 Universiteit

-0.63

 pygame

-0.63

RectangleBorder

-0.63

 VIDEOTAPE

-0.62

tvguidetime

-0.61

SourceChecksum

-0.61

iocene

-0.60

POSITIVE LOGITS

 restaurant

0.80

 restaurants

0.73

 eatery

0.62

 Restaurant

0.61

 located

0.60

 dining

0.60

 serving

0.59

 location

0.59

restaurant

0.58

 seated

0.58

Activations Density 0.217%

recommendations for dining experiences or specific food items

No Comments

No Known Activations