INDEX

Explanations

phrases that involve advising or instructing someone not to do something

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "to" followed by an action or directive

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ¦ãĤ¹

-0.85

grounds

-0.82

examination

-0.81

usage

-0.71

accompan

-0.70

æ©

-0.70

¸

-0.69

raising

-0.69

DIT

-0.69

weekly

-0.68

POSITIVE LOGITS

 bother

1.21

 worry

1.04

 mention

1.03

 interfere

0.96

 offend

0.93

bud

0.91

 exceed

0.91

 anymore

0.91

 succumb

0.91

 stray

0.89

Activations Density 0.101%

phrases that involve advising or instructing someone not to do something

phrases that include the word "to" followed by an action or directive

No Comments

No Known Activations