INDEX

Explanations

phrases related to critical evaluation or judgment

oai_token-act-pair · gpt-3.5-turbo

terms related to criticism and ethical concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

missible

-0.73

Fax

-0.69

workers

-0.65

eligible

-0.64

ilver

-0.64

apo

-0.62

anooga

-0.61

estern

-0.60

worker

-0.60

PAC

-0.59

POSITIVE LOGITS

 haha

0.81

 somew

0.78

 disclaimer

0.75

;)

0.72

 fanbase

0.70

 Konami

0.69

 subconscious

0.69

 gimmick

0.68

wee

0.67

 Sega

0.66

Activations Density 1.149%

phrases related to critical evaluation or judgment

terms related to criticism and ethical concerns

No Comments

No Known Activations