INDEX

Explanations

the word "all."

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the word "all."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

rouse

-0.70

orio

-0.62

ogram

-0.62

krit

-0.57

ocative

-0.57

osen

-0.57

SPONSORED

-0.56

agogue

-0.55

kamp

-0.55

oice

-0.55

POSITIVE LOGITS

all

2.63

ALL

2.06

all

1.67

 everything

1.64

All

1.55

All

1.49

 every

1.39

 everyone

1.37

 everybody

1.31

 EVERY

1.24

Activations Density 0.155%

the word "all."

the occurrence of the word "all."

No Comments

No Known Activations