INDEX

Explanations

short descriptive phrases followed by "More" in a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "More"

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

DragonMagazine

-0.72

keeping

-0.72

ãĥ³ãĤ¸

-0.68

Fram

-0.67

ãĥ¼ãĥĨ

-0.65

itudes

-0.65

ardless

-0.64

itud

-0.64

atan

-0.64

%]

-0.64

POSITIVE LOGITS

 importantly

1.19

 Than

1.06

 than

0.96

ado

0.94

 Definitions

0.84

 troubling

0.75

 important

0.75

 worrisome

0.73

 Thoughts

0.73

 interesting

0.72

Activations Density 0.046%

short descriptive phrases followed by "More" in a text

instances of the word "More"

No Comments

No Known Activations