INDEX

Explanations

locations in Germany, specifically focusing on the city of Hamburg and Cologne

oai_token-act-pair · gpt-3.5-turbo

references to specific cities, particularly Hamburg and Cologne

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

yip

-0.94

inition

-0.87

wright

-0.84

itton

-0.80

avery

-0.80

osition

-0.76

iries

-0.75

 constitu

-0.73

ippery

-0.71

ocally

-0.71

POSITIVE LOGITS

 Hamburg

1.13

lar

0.81

urger

0.80

£ı

0.79

 Munich

0.77

 Dresden

0.73

Bay

0.72

stem

0.72

 Marathon

0.71

Hau

0.71

Activations Density 0.013%

locations in Germany, specifically focusing on the city of Hamburg and Cologne

references to specific cities, particularly Hamburg and Cologne

No Comments

No Known Activations