INDEX

Explanations

comparative relationships

oai_token-act-pair · gpt-3.5-turbo

comparative phrases indicating increasing consequences or effects

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

ogens

-0.79

é¾įå

-0.72

ibaba

-0.70

opol

-0.69

¶æ

-0.69

IVERS

-0.69

ÃŃa

-0.69

opian

-0.69

heng

-0.68

ju

-0.68

POSITIVE LOGITS

 likelihood

0.89

 better

0.87

 clearer

0.85

 louder

0.85

 chances

0.80

 stronger

0.80

 richer

0.80

 harder

0.80

 sooner

0.75

 quicker

0.75

Activations Density 0.045%

comparative relationships

comparative phrases indicating increasing consequences or effects

No Comments

No Known Activations