INDEX

Explanations

instances of the word "Mod" with varying prefixes and suffixes

oai_token-act-pair · gpt-3.5-turbo

variations of the word "mod."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ģĸ

-0.84

ï¸

-0.75

 Lauder

-0.73

UGE

-0.66

 Mata

-0.66

holding

-0.65

izabeth

-0.64

¨

-0.64

 Bulldogs

-0.63

Ã§a

-0.62

POSITIVE LOGITS

ifiers

1.23

ifiable

1.22

icum

1.21

ding

1.19

ifications

1.18

elled

1.14

ules

1.12

ded

1.08

ifier

1.08

ifying

1.06

Activations Density 0.014%

instances of the word "Mod" with varying prefixes and suffixes

variations of the word "mod."

No Comments

No Known Activations