INDEX

Explanations

words or phrases related to ire or anger

oai_token-act-pair · gpt-3.5-turbo

instances of the substring "ir" in various contexts

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

•layer 5 - anger

No Comments

Negative Logits

 guiActiveUnfocused

-0.84

zzo

-0.73

hetti

-0.72

soDeliveryDate

-0.72

 Parad

-0.70

 Halls

-0.68

 Opera

-0.67

ezvous

-0.66

ership

-0.65

 Remastered

-0.65

POSITIVE LOGITS

idium

1.02

cles

0.98

ked

0.91

acet

0.86

ilateral

0.81

respective

0.80

itably

0.79

respons

0.79

religious

0.78

acial

0.78

Activations Density 0.009%

words or phrases related to ire or anger

instances of the substring "ir" in various contexts

No Comments

No Known Activations