INDEX

Explanations

prepositions used in phrases like "up-to-date" or "up-and-coming."

oai_token-act-pair · gpt-3.5-turbo

phrases related to raising awareness or updates about products or trends

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulhu

-0.71

Wiz

-0.71

Phi

-0.69

 Protective

-0.69

 Archdemon

-0.66

 EntityItem

-0.66

 Canaveral

-0.65

 Juliet

-0.64

 existence

-0.62

 Eternity

-0.62

POSITIVE LOGITS

stairs

1.14

graded

1.11

sized

1.11

tem

1.09

raised

1.03

grade

1.03

grading

0.98

turned

0.98

ranked

0.98

level

0.97

Activations Density 0.079%

prepositions used in phrases like "up-to-date" or "up-and-coming."

phrases related to raising awareness or updates about products or trends

No Comments

No Known Activations