INDEX

Explanations

phrases containing the word "the", likely without focusing on any particular type of context

oai_token-act-pair · gpt-3.5-turbo

instances 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

craft

-0.66

-0.63

âĢĳ

-0.62

arry

-0.59

 Judaism

-0.56

 versus

-0.56

and

-0.55

 arises

-0.54

HAEL

-0.53

POSITIVE LOGITS

 same

1.38

 entire

1.13

 slightest

1.13

ses

1.12

 latter

1.12

 entirety

1.10

 hardest

1.06

 easiest

1.05

 fastest

1.05

 strongest

1.04

Activations Density 0.644%

phrases containing the word "the", likely without focusing on any particular type of context

instances of the word "the."

No Comments

No Known Activations