INDEX

Explanations

instances of the word "it" followed by an action or situation

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the word "it" as a subject 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

behind

-0.73

holding

-0.72

Priv

-0.70

cox

-0.68

transfer

-0.64

igmatic

-0.62

SHARE

-0.61

hips

-0.60

dit

-0.60

icons

-0.59

POSITIVE LOGITS

chy

1.10

 happened

1.01

alian

1.00

 happens

0.99

 happ

0.93

 mattered

0.89

 rains

0.88

 wasn

0.86

ain

0.85

 seems

0.85

Activations Density 0.181%

instances of the word "it" followed by an action or situation

phrases that emphasize the word "it" as a subject in various contexts

No Comments

No Known Activations