INDEX

Explanations

phrases related to specific countries, with a particular focus on Lebanon

oai_token-act-pair · gpt-3.5-turbo

references to Lebanon and its associated context

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

vich

-0.79

uristic

-0.78

ointed

-0.76

Oracle

-0.71

ramid

-0.70

oted

-0.70

ellation

-0.70

gers

-0.70

ierrez

-0.69

lasses

-0.68

POSITIVE LOGITS

 ILCS

0.84

 Lebanon

0.84

ites

0.82

isi

0.74

anca

0.74

 Leban

0.73

 Hezbollah

0.72

 Beirut

0.70

azard

0.69

 Lebanese

0.68

Activations Density 0.013%

phrases related to specific countries, with a particular focus on Lebanon

references to Lebanon and its associated context

No Comments

No Known Activations