INDEX

Explanations

phrases or sentences with strong emphasis, often expressing approval or affirmation, and potentially personal thoughts or reactions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

emis

-0.86

hips

-0.80

isively

-0.72

lems

-0.72

kamp

-0.70

greg

-0.70

atur

-0.69

este

-0.68

xes

-0.68

ILY

-0.66

POSITIVE LOGITS

 pesky

1.03

 sounds

1.03

 bastard

0.95

 fateful

0.94

 sounded

0.93

guy

0.87

cher

0.84

guy

0.83

 reminds

0.82

 sucks

0.79

Activations Density 0.156%

phrases or sentences with strong emphasis, often expressing approval or affirmation, and potentially personal thoughts or reactions

instances of the word "that."

No Comments

No Known Activations