INDEX

Explanations

phrases related to conflict, controversy, and sparking reactions or debates

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to igniting debates or controversies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Norn

-0.79

 sake

-0.77

 ancestors

-0.76

 uncond

-0.74

 coefficients

-0.74

enance

-0.71

 embodiments

-0.70

 values

-0.66

 eliminates

-0.65

 purposes

-0.65

POSITIVE LOGITS

 controversy

1.46

 debate

1.25

 uproar

1.24

 dispute

1.23

 frenzy

1.18

 rift

1.17

 saga

1.16

 backlash

1.14

 brawl

1.14

 feud

1.11

Activations Density 0.330%

phrases related to conflict, controversy, and sparking reactions or debates

words and phrases related to igniting debates or controversies

No Comments

No Known Activations