INDEX

Explanations

the word "that" or phrases with "just that."

oai_token-act-pair · gpt-3.5-turbo

phrases indicating certainty or emphasis

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

NYSE

-0.71

ighed

-0.69

abama

-0.69

issance

-0.67

rees

-0.62

ãĤ¨ãĥ«

-0.60

Ã»

-0.60

ãĥ¼ãĥĨ

-0.60

vironments

-0.58

ashington

-0.58

POSITIVE LOGITS

iator

0.61

 messenger

0.60

 fateful

0.59

sie

0.58

 happens

0.55

cher

0.55

 reversed

0.55

chuk

0.54

chers

0.53

Wid

0.52

Activations Density 0.065%

the word "that" or phrases with "just that."

phrases indicating certainty or emphasis

No Comments

No Known Activations