INDEX

Explanations

words related to conflicts and disagreements

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to conflicts or disputes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

CHO

-0.71

vale

-0.70

elin

-0.68

IDS

-0.66

erton

-0.63

 Alto

-0.62

 Assist

-0.62

eele

-0.62

anium

-0.61

vana

-0.60

POSITIVE LOGITS

 between

1.36

between

1.08

roy

1.03

 over

0.99

 raging

0.98

SHIP

0.98

hips

0.96

 waged

0.94

 erupt

0.93

 brewing

0.93

Activations Density 0.193%

words related to conflicts and disagreements

words and phrases related to conflicts or disputes

No Comments

No Known Activations