INDEX

Explanations

targeted keywords related to specific entities, locations, and roles mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

specific nouns and proper names related to various subjects and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 thous

-0.51

ationally

-0.47

 seiz

-0.45

aples

-0.43

buquerque

-0.43

yss

-0.43

illin

-0.43

wcsstore

-0.42

à¨

-0.41

oret

-0.41

POSITIVE LOGITS

1.04

*.

1.03

%.

0.98

+.

0.98

.[

0.95

'.

0.88

.*

0.87

.).

0.87

.(

0.86

.'

0.85

Activations Density 1.484%

targeted keywords related to specific entities, locations, and roles mentioned in the text

specific nouns and proper names related to various subjects and affiliations

No Comments

No Known Activations