INDEX

Explanations

locations with the word "Inn"

oai_token-act-pair · gpt-3.5-turbo

references to various inns or accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

vich

-0.79

 litter

-0.76

uyomi

-0.74

 Stafford

-0.72

izoph

-0.68

 Typhoon

-0.65

 Shutterstock

-0.63

 Reason

-0.63

=-=-=-=-=-=-=-=-

-0.62

Mub

-0.62

POSITIVE LOGITS

umerable

1.30

ocent

1.21

keeper

1.12

okin

1.05

itial

1.04

oc

1.02

umerous

0.95

ologue

0.94

isf

0.93

umer

0.91

Activations Density 0.018%

locations with the word "Inn"

references to various inns or accommodations

No Comments

No Known Activations