INDEX

Explanations

mentions or references to the brand "Cheerios"

oai_token-act-pair · gpt-3.5-turbo

word endings, particularly those associated with various forms and plurals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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´

-0.84

ICES

-0.74

$$$$

-0.73

ãĤ¼ãĤ¦ãĤ¹

-0.72

ãĤ¤ãĥĪ

-0.71

 Amend

-0.70

ãĥĩ

-0.69

EGIN

-0.67

ãĤ®

-0.66

MENTS

-0.65

POSITIVE LOGITS

ghan

0.86

kee

0.80

ebus

0.76

ldon

0.75

vern

0.73

zy

0.73

eworthy

0.73

zers

0.72

zzo

0.70

zel

0.70

Activations Density 0.115%

mentions or references to the brand "Cheerios"

word endings, particularly those associated with various forms and plurals

No Comments

No Known Activations