INDEX

Explanations

places and organizations with the word "National" in their names

oai_token-act-pair · gpt-3.5-turbo

references to national parks or notable national landmarks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icularly

-0.73

onal

-0.70

aphael

-0.66

adish

-0.64

utenberg

-0.64

 grat

-0.63

leneck

-0.63

bol

-0.61

Bloomberg

-0.60

ppings

-0.60

POSITIVE LOGITS

 Speedway

0.80

 Resort

0.74

 Complex

0.67

 Prison

0.67

ities

0.67

Lear

0.66

ITIES

0.66

 Corpus

0.65

 Intermediate

0.65

eport

0.64

Activations Density 0.088%

places and organizations with the word "National" in their names

references to national parks or notable national landmarks

No Comments

No Known Activations