INDEX

Explanations

the term "mod" or variations of the word "modified"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "mod" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ï¸

-0.91

âĸ¬

-0.77

ģĸ

-0.75

éĽ

-0.74

OHN

-0.73

âķĲâķĲ

-0.71

 Unic

-0.70

Ã§a

-0.70

 Oaks

-0.68

 Mata

-0.68

POSITIVE LOGITS

ifications

1.17

ifiers

1.15

ding

1.15

ifiable

1.15

icum

1.08

elled

1.06

ifier

1.05

erate

1.03

ifying

1.03

esty

1.02

Activations Density 0.008%

the term "mod" or variations of the word "modified"

variations of the word "mod" in different contexts

No Comments

No Known Activations