INDEX

Explanations

instances where a statement contradicts something in the text

oai_token-act-pair · gpt-3.5-turbo

the word "not" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

tein

-0.81

rift

-0.78

ixel

-0.78

arten

-0.70

istle

-0.68

TIME

-0.67

 Tycoon

-0.66

Times

-0.66

ngth

-0.63

velt

-0.62

POSITIVE LOGITS

 necessarily

1.29

icable

1.05

etheless

1.04

epad

0.96

eworthy

0.94

icably

0.90

withstanding

0.89

 enough

0.84

cially

0.78

 bothering

0.75

Activations Density 0.045%

instances where a statement contradicts something in the text

the word "not" in various contexts

No Comments

No Known Activations