INDEX

Explanations

phrases indicating future progress or direction

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate future actions or directions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ulin

-0.73

uminati

-0.70

eness

-0.68

ules

-0.67

oola

-0.66

ises

-0.65

trak

-0.62

uum

-0.61

odor

-0.59

oup

-0.58

POSITIVE LOGITS

 forward

1.32

forward

1.27

 into

1.20

 forwards

1.13

 Into

1.01

 Forward

0.98

into

0.97

 INTO

0.96

 onward

0.95

 onwards

0.91

Activations Density 0.079%

phrases indicating future progress or direction

phrases that indicate future actions or directions

No Comments

No Known Activations