INDEX

Explanations

words related to names and terms that contain 'co' in them

oai_token-act-pair · gpt-3.5-turbo

words related to "co" or regions associated with various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Skydragon

-0.79

 Hungarian

-0.72

 GOODMAN

-0.67

 Ninth

-0.65

acious

-0.65

 EntityItem

-0.64

gements

-0.63

 Greek

-0.62

senal

-0.62

 Reincarn

-0.62

POSITIVE LOGITS

xon

1.24

ffee

1.18

oldown

1.10

operative

1.05

fman

1.01

zzi

1.00

verage

1.00

operation

0.97

pper

0.93

oper

0.91

Activations Density 0.013%

words related to names and terms that contain 'co' in them

words related to "co" or regions associated with various contexts

No Comments

No Known Activations