INDEX

Explanations

phrases related to decision-making or planning

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

©¶æ

-0.81

neg

-0.62

uli

-0.61

ĨĴ

-0.60

Drag

-0.60

Deg

-0.60

nia

-0.60

Hop

-0.60

mx

-0.58

idas

-0.57

POSITIVE LOGITS

 è£ıè

0.65

ively

0.60

 underwater

0.60

EStream

0.59

DPR

0.58

ivities

0.58

xp

0.57

 pokemon

0.56

anse

0.56

...

0.53

Activations Density 0.167%

phrases related to decision-making or planning

No Comments

No Known Activations