INDEX

Explanations

phrases related to a specific location, specifically Manila

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Manila."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

heimer

-0.81

Ö¼

-0.80

RH

-0.78

chool

-0.76

ership

-0.76

áµ

-0.75

schild

-0.73

ordan

-0.72

ueller

-0.71

eer

-0.71

POSITIVE LOGITS

 Manila

1.32

 Philippines

1.08

 Philippine

0.99

 Filip

0.98

 Filipino

0.98

 Duterte

0.96

pes

0.96

 Marcos

0.94

 Islands

0.91

 Lumpur

0.89

Activations Density 0.015%

phrases related to a specific location, specifically Manila

occurrences of the word "Manila."

No Comments

No Known Activations