INDEX

Explanations

phrases containing the word "hey."

oai_token-act-pair · gpt-3.5-turbo

the word "hey" and its variations, indicating informal or conversational tone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

icist

-0.67

 Destroyer

-0.65

RAW

-0.64

 Biol

-0.64

 understatement

-0.64

 submarines

-0.64

Ø¨

-0.63

âĢ¢âĢ¢âĢ¢âĢ¢

-0.61

Bound

-0.60

CENT

-0.60

POSITIVE LOGITS

hey

1.23

pants

0.92

pole

0.88

terness

0.86

endas

0.85

ther

0.83

boys

0.81

dden

0.80

etooth

0.79

nuts

0.79

Activations Density 0.009%

phrases containing the word "hey."

the word "hey" and its variations, indicating informal or conversational tone

No Comments

No Known Activations