INDEX

Explanations

negations or exceptions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating negation or the absence of something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ixel

-0.76

tein

-0.72

rift

-0.68

tty

-0.67

creen

-0.66

velt

-0.66

istle

-0.64

stone

-0.64

Run

-0.64

arten

-0.64

POSITIVE LOGITS

 necessarily

1.31

icable

1.19

icably

1.13

etheless

1.04

epad

1.04

eworthy

1.02

withstanding

0.97

 bothering

0.77

 exactly

0.77

 bothered

0.77

Activations Density 0.044%

negations or exceptions

phrases indicating negation or the absence of something

No Comments

No Known Activations