INDEX

Explanations

mentions of pancakes and syrup

oai_token-act-pair · gpt-3.5-turbo

references to pancakes and syrup

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

ment

-0.86

stra

-0.80

ments

-0.79

mint

-0.78

nuts

-0.77

 Trader

-0.76

nut

-0.71

culosis

-0.70

chin

-0.69

ious

-0.69

POSITIVE LOGITS

 syrup

0.93

 pancakes

0.88

ĸļ

0.83

ipedia

0.76

aye

0.75

XT

0.75

 panc

0.71

akeru

0.70

rase

0.70

bsite

0.67

Activations Density 0.040%

mentions of pancakes and syrup

references to pancakes and syrup

No Comments

No Known Activations