INDEX

Explanations

instances where something is being added or contributed in addition to something else

oai_token-act-pair · gpt-3.5-turbo

the word "also" and similar terms that indicate addition or inclusion

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

soDeliveryDate

-0.80

DragonMagazine

-0.74

conservancy

-0.74

 Apostle

-0.70

IOC

-0.69

isSpecialOrderable

-0.64

 Tribune

-0.62

CST

-0.61

DAQ

-0.61

 Ninth

-0.61

POSITIVE LOGITS

pher

0.97

ouncing

0.94

ashing

0.90

ulating

0.88

picking

0.87

asing

0.85

icating

0.85

angering

0.84

paying

0.83

ying

0.82

Activations Density 0.294%

instances where something is being added or contributed in addition to something else

the word "also" and similar terms that indicate addition or inclusion

No Comments

No Known Activations