INDEX

Explanations

the word "each" followed by a number

oai_token-act-pair · gpt-3.5-turbo

instances of the word "each" indicating quantities or distributions

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

holes

-0.71

 Blaz

-0.70

stones

-0.70

Ruk

-0.70

ahime

-0.68

Bs

-0.67

abad

-0.65

hawks

-0.64

YN

-0.63

 Roberts

-0.63

POSITIVE LOGITS

 thereafter

0.86

 weekday

0.86

è¦ļéĨĴ

0.75

uana

0.73

*/(

0.72

 successive

0.72

uania

0.72

ioxide

0.71

 paycheck

0.70

Ĥİ

0.69

Activations Density 0.029%

the word "each" followed by a number

instances of the word "each" indicating quantities or distributions

No Comments

No Known Activations