INDEX

Explanations

locations, specifically mentioning large retail stores like Walmart and Target

oai_token-act-pair · gpt-3.5-turbo

the mentions of Walmart and its context within various situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

odic

-0.93

ydia

-0.77

arial

-0.77

odox

-0.76

bil

-0.74

adal

-0.71

iod

-0.66

 orally

-0.65

ews

-0.64

adic

-0.64

POSITIVE LOGITS

 Stores

1.15

halla

0.89

 stores

0.87

 Store

0.84

mart

0.83

 store

0.83

Leaks

0.80

store

0.80

Shop

0.77

 Restaur

0.75

Activations Density 0.006%

locations, specifically mentioning large retail stores like Walmart and Target

the mentions of Walmart and its context within various situations

No Comments

No Known Activations