INDEX

Explanations

instances where actions are being described or discussed

oai_token-act-pair · gpt-3.5-turbo

modal verbs indicating capability or possibility

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

 downside

-0.67

 cautioned

-0.64

 contraction

-0.64

 deficit

-0.64

 irony

-0.63

 aside

-0.60

 doubted

-0.59

 disson

-0.59

 Apart

-0.58

repre

-0.58

POSITIVE LOGITS

't

1.06

ilater

0.95

 satisfy

0.85

 safely

0.83

 emulate

0.81

 accommodate

0.81

ivery

0.80

itate

0.77

sylv

0.77

 cope

0.77

Activations Density 0.103%

instances where actions are being described or discussed

modal verbs indicating capability or possibility

No Comments

No Known Activations