INDEX

Explanations

occurrences of the word "curious" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to curiosity or inquisitive themes

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

ffen

-0.68

boarding

-0.66

reditation

-0.63

board

-0.62

adier

-0.62

Roy

-0.61

AW

-0.61

 Surv

-0.60

lag

-0.60

 helicop

-0.60

POSITIVE LOGITS

 curiosity

1.11

 onlook

0.92

 probing

0.86

 curious

0.84

iously

0.84

 Curious

0.82

Magikarp

0.77

ity

0.76

ities

0.75

ioned

0.73

Activations Density 0.019%

occurrences of the word "curious" in various contexts

references to curiosity or inquisitive themes

No Comments

No Known Activations