INDEX

Explanations

the word "the" with different intensities

oai_token-act-pair · gpt-3.5-turbo

the word "the" in various contexts throughout the document

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

ornings

-0.53

Ò

-0.49

*.

-0.49

worth

-0.48

antes

-0.48

 beforehand

-0.47

 with

-0.46

thood

-0.46

qi

-0.46

 conclud

-0.46

POSITIVE LOGITS

 same

0.94

 slightest

0.85

 latter

0.84

 latest

0.79

 hottest

0.78

 biggest

0.78

 quickest

0.78

 smallest

0.77

 fastest

0.77

oret

0.77

Activations Density 1.277%

the word "the" with different intensities

the word "the" in various contexts throughout the document

No Comments

No Known Activations