INDEX

Explanations

references to the word "Viridian" or variations of it in the text

oai_token-act-pair · gpt-3.5-turbo

references to the term "Viridian" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

*/(

-0.91

uyomi

-0.91

 quarters

-0.71

oppers

-0.70

OWER

-0.70

cedented

-0.69

orative

-0.68

aration

-0.66

ylan

-0.66

owment

-0.65

POSITIVE LOGITS

gil

1.14

cles

0.85

ulence

0.84

Vir

0.84

idian

0.83

gins

0.83

alde

0.81

ulent

0.79

git

0.76

nces

0.76

Activations Density 0.006%

references to the word "Viridian" or variations of it in the text

references to the term "Viridian" and variations of it

No Comments

No Known Activations