INDEX

Explanations

the word "that" followed by an explanation or statement

oai_token-act-pair · gpt-3.5-turbo

phrases or sentences that use the word "that."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ´ãĥ³

-0.84

izont

-0.83

aukee

-0.72

ocaust

-0.71

ovember

-0.66

PRESS

-0.65

estern

-0.63

TPPStreamerBot

-0.62

neau

-0.62

erenn

-0.62

POSITIVE LOGITS

 consequently

0.94

soever

0.86

 they

0.84

 furthermore

0.78

 reconc

0.73

 moreover

0.72

 therefore

0.72

 justifies

0.70

cher

0.70

 culminated

0.69

Activations Density 0.101%

the word "that" followed by an explanation or statement

phrases or sentences that use the word "that."

No Comments

No Known Activations