INDEX

Explanations

words related to intense emotions, particularly anger

oai_token-act-pair · gpt-3.5-turbo

instances of the word "rage" along with related emotional expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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 4 - anger

No Comments

Negative Logits

icut

-0.85

ramer

-0.83

herty

-0.79

rica

-0.71

 coerc

-0.71

lder

-0.68

nai

-0.68

pse

-0.67

arent

-0.67

 Liberties

-0.66

POSITIVE LOGITS

quit

1.06

 rage

1.00

 fury

0.89

 raging

0.81

 furnace

0.80

ï¸

0.78

bol

0.77

TEXTURE

0.76

ously

0.72

 vengeance

0.71

Activations Density 0.019%

words related to intense emotions, particularly anger

instances of the word "rage" along with related emotional expressions

No Comments

No Known Activations