INDEX

Explanations

mentions of specific food items

oai_token-act-pair · gpt-3.5-turbo

food items, particularly specific dishes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 seism

-0.78

 Aerospace

-0.75

 Weld

-0.72

EEG

-0.71

 Telecommunications

-0.71

 defect

-0.69

 anomal

-0.67

agnetic

-0.66

 Morse

-0.65

 Koen

-0.63

POSITIVE LOGITS

 sandwiches

1.16

 meal

1.14

 noodles

1.14

isine

1.11

 sandwich

1.10

 Soup

1.09

 soup

1.07

 tasted

1.05

 salad

1.04

 tasting

1.04

Activations Density 0.243%

mentions of specific food items

food items, particularly specific dishes

No Comments

No Known Activations