INDEX

Explanations

phrases related to diplomatic relations

oai_token-act-pair · gpt-3.5-turbo

references to diplomatic matters and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alach

-0.78

isode

-0.73

corn

-0.71

amaz

-0.71

gger

-0.71

nings

-0.70

liga

-0.70

oven

-0.67

runs

-0.66

omi

-0.66

POSITIVE LOGITS

 diplomatic

1.02

 corps

0.98

 diplomacy

0.97

plom

0.95

 embassy

0.92

 diplomats

0.87

 embassies

0.84

 reception

0.84

 cables

0.81

 relations

0.79

Activations Density 0.022%

phrases related to diplomatic relations

references to diplomatic matters and activities

No Comments

No Known Activations