INDEX

Explanations

phrases related to controversial political topics and policies

oai_token-act-pair · gpt-3.5-turbo

key terms and phrases related to healthcare policy and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 greets

-0.81

 sidx

-0.81

DragonMagazine

-0.73

elight

-0.72

Adds

-0.71

irtual

-0.69

ributes

-0.67

 Adds

-0.66

rouse

-0.66

autions

-0.66

POSITIVE LOGITS

 deteriorating

1.37

 unsustainable

1.36

 rotten

1.35

 dysfunctional

1.31

 doomed

1.28

 flawed

1.28

 defective

1.27

 deficient

1.25

 screwed

1.24

 crumbling

1.24

Activations Density 0.523%

phrases related to controversial political topics and policies

key terms and phrases related to healthcare policy and its implications

No Comments

No Known Activations