INDEX

Explanations

words and phrases related to raising questions or concerns

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate raising questions or doubts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 vanquished

-0.70

 survives

-0.65

\-

-0.62

melon

-0.62

ta

-0.62

 Healer

-0.61

ians

-0.60

ian

-0.60

 conquered

-0.60

 Thou

-0.60

POSITIVE LOGITS

 suspicions

1.34

 eyebrows

1.29

 doubts

1.22

 suspicion

1.15

 questions

1.14

 alarms

1.12

 alarm

1.10

 concerns

1.07

 fears

1.00

 tensions

0.94

Activations Density 0.068%

words and phrases related to raising questions or concerns

phrases that indicate raising questions or doubts

No Comments

No Known Activations