INDEX

Explanations

phrases related to refusing or rejecting something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "turned down."

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

anwhile

-0.76

velt

-0.73

upper

-0.72

insk

-0.72

Known

-0.68

ollen

-0.65

 Towns

-0.65

 Kills

-0.64

puted

-0.64

atures

-0.63

POSITIVE LOGITS

 bribes

0.72

fax

0.67

 requests

0.66

 extradition

0.64

 refunds

0.62

 Kraft

0.61

 waivers

0.61

 liking

0.61

\">

0.60

 Blumenthal

0.60

Activations Density 0.024%

phrases related to refusing or rejecting something

instances of the phrase "turned down."

No Comments

No Known Activations