INDEX

Explanations

phrases related to specific food items and ingredients

oai_token-act-pair · gpt-3.5-turbo

food-related terms and ingredients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FUN

-0.74

 Lands

-0.65

 FIRE

-0.64

 departures

-0.63

Student

-0.62

IRC

-0.62

£ı

-0.62

DATA

-0.62

quickShipAvailable

-0.61

ctive

-0.61

POSITIVE LOGITS

ensis

0.88

worm

0.78

atum

0.73

stro

0.72

quartered

0.71

chery

0.71

itaire

0.71

 jelly

0.70

chlor

0.67

worms

0.67

Activations Density 0.389%

phrases related to specific food items and ingredients

food-related terms and ingredients

No Comments

No Known Activations