INDEX

Explanations

information related to the United States, such as data, activities, locations, and specific occurrences happening in the country

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

ibl

-0.72

Iterator

-0.71

govtrack

-0.71

#$

-0.70

 partName

-0.68

witch

-0.66

ÏĢ

-0.64

 listens

-0.63

fn

-0.62

\-

-0.62

POSITIVE LOGITS

 same

1.26

 Philippines

1.11

 latter

1.07

 latest

1.02

 United

1.01

 country

1.00

 poorest

1.00

 aforementioned

0.99

 largest

0.96

 heaviest

0.96

Activations Density 1.055%

information related to the United States, such as data, activities, locations, and specific occurrences happening in the country

occurrences of the word "the."

No Comments

No Known Activations