INDEX

Explanations

phrases related to investigations and legal matters

oai_token-act-pair · gpt-3.5-turbo

the phrase "In" followed by a numerical value or a significant time reference

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

 spoil

-0.70

 looms

-0.67

reon

-0.64

-0.63

channelAvailability

-0.63

lov

-0.60

 unlocks

-0.59

:/

-0.59

pim

-0.58

 litter

-0.57

POSITIVE LOGITS

 addition

1.28

juries

1.21

ventory

1.21

herent

1.19

flation

1.19

 spite

1.17

cluding

1.15

jured

1.14

 contrast

1.13

clusion

1.13

Activations Density 0.165%

phrases related to investigations and legal matters

the phrase "In" followed by a numerical value or a significant time reference

No Comments

No Known Activations