INDEX

Explanations

words related to locations or landmarks

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "at."

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

å£«

-0.73

 Tsukuyomi

-0.72

SPONSORED

-0.68

er

-0.65

Blade

-0.64

vous

-0.62

omething

-0.60

ppelin

-0.59

BUT

-0.58

GROUP

-0.56

POSITIVE LOGITS

abase

1.27

rix

1.22

rice

1.21

rices

1.14

oday

1.11

hemat

1.09

rition

1.04

hetically

1.02

mosp

1.01

terson

0.98

Activations Density 0.057%

words related to locations or landmarks

occurrences of the word "at."

No Comments

No Known Activations