INDEX

Explanations

definite articles 'the'

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the" in various contexts

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

mares

-0.78

 besides

-0.68

 whatsoever

-0.66

worn

-0.64

craft

-0.64

 conceive

-0.64

 whilst

-0.63

 assumes

-0.63

amazon

-0.63

rade

-0.62

POSITIVE LOGITS

 strongest

1.16

 fastest

1.16

 happiest

1.13

 same

1.13

 hardest

1.12

 hottest

1.12

 smartest

1.11

 largest

1.08

 biggest

1.08

 highest

1.07

Activations Density 0.243%

definite articles 'the'

instances of the word "the" in various contexts

No Comments

No Known Activations