INDEX

Explanations

phrases or sentences with a specific format of symbols, likely as markers for text processing or organization

oai_token-act-pair · gpt-3.5-turbo

instances of dramatic tension or conflict in narratives

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wagen

-0.81

ulkan

-0.75

 grouping

-0.72

ertodd

-0.72

utory

-0.72

irm

-0.69

ĪĴ

-0.67

 bloc

-0.66

uly

-0.66

awei

-0.64

POSITIVE LOGITS

SPONSORED

0.95

Trivia

0.88

Discover

0.77

Cover

0.75

Elsa

0.74

rawdownloadcloneembedreportprint

0.73

Film

0.72

COLOR

0.71

PHOTOS

0.71

Hum

0.71

Activations Density 0.355%

phrases or sentences with a specific format of symbols, likely as markers for text processing or organization

instances of dramatic tension or conflict in narratives

No Comments

No Known Activations