INDEX

Explanations

proper nouns related to political figures and government positions

oai_token-act-pair · gpt-3.5-turbo

references to significant political figures and their roles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĸ¬

-0.76

VID

-0.73

LOAD

-0.71

NAT

-0.69

ISP

-0.64

VID

-0.63

Sensor

-0.63

 reproduction

-0.60

Ow

-0.60

frame

-0.60

POSITIVE LOGITS

 Tillerson

1.17

 Jinping

0.86

ython

0.81

ongyang

0.80

eln

0.80

uchin

0.79

 DeVos

0.79

 memos

0.78

utations

0.77

erella

0.77

Activations Density 0.022%

proper nouns related to political figures and government positions

references to significant political figures and their roles

No Comments

No Known Activations