INDEX

Explanations

instances where an action or event is being described as the first time it has occurred

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "when I first" or variations thereof

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

 Canaver

-0.75

 Vish

-0.69

 Brah

-0.67

RAM

-0.66

 Rodrigo

-0.64

asty

-0.63

crim

-0.62

 Gould

-0.62

 à¤

-0.62

oute

-0.61

POSITIVE LOGITS

 responders

1.03

 baseman

0.99

 glance

0.96

 blush

0.86

 glim

0.80

 lady

0.78

arily

0.76

 estab

0.75

 embark

0.75

 encount

0.74

Activations Density 0.027%

instances where an action or event is being described as the first time it has occurred

instances of the phrase "when I first" or variations thereof

No Comments

No Known Activations