INDEX

Explanations

phrases related to possibility or capability

oai_token-act-pair · gpt-3.5-turbo

expressions of certainty and the need for specific conditions to be met

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨãĤ£

-0.48

ãĥ³ãĤ¸

-0.48

Sund

-0.47

ãĥīãĥ©

-0.45

vari

-0.42

Moon

-0.41

pload

-0.41

 metic

-0.41

itialized

-0.39

aution

-0.39

POSITIVE LOGITS

0.57

,''

0.50

 because

0.49

--

0.49

...

0.49

......

0.49

....

0.47

 whatsoever

0.47

iatus

0.47

Activations Density 1.532%

phrases related to possibility or capability

expressions of certainty and the need for specific conditions to be met

No Comments

No Known Activations