INDEX

Explanations

enumerated lists

oai_token-act-pair · gpt-3.5-turbo

references to numerical values or items in parentheses

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

adiq

-0.71

iences

-0.70

azon

-0.69

bos

-0.68

ciating

-0.66

cms

-0.63

oscope

-0.62

edi

-0.62

usher

-0.61

rencies

-0.60

POSITIVE LOGITS

 Rings

0.64

ãĥİ

0.63

 IMAGES

0.62

 ILCS

0.61

 Deaths

0.60

neg

0.59

 Frames

0.59

 McKenzie

0.58

 Aberdeen

0.56

 Seek

0.55

Activations Density 0.077%

enumerated lists

references to numerical values or items in parentheses

No Comments

No Known Activations