INDEX

Explanations

references to the retail store "Walmart"

oai_token-act-pair · gpt-3.5-turbo

references to Walmart and related retail terminology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ibilities

-0.84

bil

-0.84

odic

-0.83

odox

-0.75

hw

-0.72

adal

-0.70

rough

-0.70

kj

-0.69

æŃ

-0.68

ydia

-0.68

POSITIVE LOGITS

 Stores

1.41

 stores

1.08

 shoppers

0.98

 store

0.97

 Shopping

0.92

 malls

0.90

 shelves

0.87

 Restaur

0.87

 pharmacy

0.83

 vouchers

0.83

Activations Density 0.025%

references to the retail store "Walmart"

references to Walmart and related retail terminology

No Comments

No Known Activations