INDEX

Explanations

occurrences of the word "the" with high activation values

oai_token-act-pair · gpt-3.5-turbo

the definite article "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

iffe

-0.77

thood

-0.63

aba

-0.60

leeve

-0.58

 Pastebin

-0.58

claw

-0.57

craft

-0.57

bee

-0.56

Edit

-0.55

 assume

-0.55

POSITIVE LOGITS

 same

1.16

ses

1.08

 longest

1.05

 hardest

1.01

 fastest

1.00

 entire

0.96

 entirety

0.96

 quickest

0.95

 slightest

0.94

 latter

0.94

Activations Density 0.244%

occurrences of the word "the" with high activation values

the definite article "the"

No Comments

No Known Activations