INDEX

Explanations

instances where the word "curious" or related forms of the word are used

oai_token-act-pair · gpt-3.5-turbo

expressions of curiosity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ffen

-0.76

adier

-0.75

 preached

-0.69

©¶æ

-0.67

 helicop

-0.64

Roy

-0.63

ufact

-0.62

assad

-0.62

ruction

-0.61

AW

-0.61

POSITIVE LOGITS

 curiosity

1.07

 onlook

0.92

 probing

0.86

 curious

0.86

 Curious

0.80

 passers

0.79

 Interest

0.77

iously

0.76

ities

0.73

ioned

0.72

Activations Density 0.010%

instances where the word "curious" or related forms of the word are used

expressions of curiosity

No Comments

No Known Activations