INDEX

Explanations

occurrences of the word "THE" in the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the" and related variations, indicating a focus on specific subjects or entities

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

perties

-0.73

 Kern

-0.66

 Schwar

-0.65

alk

-0.63

hm

-0.62

lets

-0.61

angan

-0.60

fired

-0.60

eca

-0.59

due

-0.58

POSITIVE LOGITS

HEAD

1.44

 THERE

1.41

THE

1.39

 FANTASY

1.37

FORM

1.36

ERSON

1.35

 ABOUT

1.34

 REPORT

1.33

 PRESIDENT

1.31

WORK

1.31

Activations Density 0.155%

occurrences of the word "THE" in the text

instances of the word "the" and related variations, indicating a focus on specific subjects or entities

No Comments

No Known Activations