INDEX

Explanations

instances where the phrase "in its" is followed by a specific adjective phrase

oai_token-act-pair · gpt-3.5-turbo

references to "its" and variations of "own."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tch

-0.74

ominated

-0.71

SHIP

-0.67

 TEAM

-0.65

 Guys

-0.64

finger

-0.63

illed

-0.62

 Doctors

-0.62

bet

-0.61

rain

-0.60

POSITIVE LOGITS

 entirety

1.69

 infancy

1.37

 totality

1.18

 simplest

1.12

 inception

1.11

 widest

1.03

 rightful

1.01

own

1.01

 fullest

0.98

 essence

0.95

Activations Density 0.065%

instances where the phrase "in its" is followed by a specific adjective phrase

references to "its" and variations of "own."

No Comments

No Known Activations