INDEX

Explanations

the word "not" followed by a high activation word

oai_token-act-pair · gpt-3.5-turbo

the phrase "not only" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

stakes

-0.67

 Quarterly

-0.67

 Budapest

-0.60

plate

-0.58

 Grimoire

-0.57

ixel

-0.57

 Frenzy

-0.55

ç·

-0.55

 Spotlight

-0.54

 Pulse

-0.54

POSITIVE LOGITS

epad

1.42

icably

1.41

ched

1.18

ices

1.17

ches

1.16

hin

1.15

ifying

1.15

ifies

1.15

ifications

1.10

ifier

1.07

Activations Density 0.129%

the word "not" followed by a high activation word

the phrase "not only" and its variations

No Comments

No Known Activations