INDEX

Explanations

questions expressing curiosity or seeking information about the nature or type of something

oai_token-act-pair · gpt-3.5-turbo

phrases relating to types or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eni

-0.77

orest

-0.76

ĸļ

-0.73

enes

-0.72

esty

-0.71

pak

-0.70

cius

-0.70

arest

-0.69

 Pigs

-0.69

ences

-0.67

POSITIVE LOGITS

 thing

0.78

 relationship

0.72

 luck

0.72

 manners

0.68

 surprises

0.68

 millenn

0.68

 monster

0.67

 deal

0.66

 goodies

0.65

 sleeper

0.64

Activations Density 0.043%

questions expressing curiosity or seeking information about the nature or type of something

phrases relating to types or categories

No Comments

No Known Activations