INDEX

Explanations

titles or headings within the text

oai_token-act-pair · gpt-3.5-turbo

the word "The" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

/"

-0.75

 without

-0.67

gpu

-0.66

eno

-0.66

âĢ¦.

-0.64

alone

-0.64

 beforehand

-0.64

 with

-0.63

—"

-0.61

omever

-0.61

POSITIVE LOGITS

oret

1.58

odore

1.33

resa

1.33

ories

1.16

atre

1.09

orem

1.07

 easiest

1.07

 simplest

1.03

 biggest

1.03

 earliest

1.00

Activations Density 0.412%

titles or headings within the text

the word "The" in various contexts

No Comments

No Known Activations