INDEX

Explanations

mentions of the television show "Dragon Ball Super"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Dragon" related to the context of the "Dragon Ball Super" series

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

ablished

-0.79

oci

-0.74

ablishment

-0.71

 Trinidad

-0.70

rontal

-0.67

ALS

-0.67

EMS

-0.67

 Tanz

-0.67

 Crosby

-0.67

zsche

-0.67

POSITIVE LOGITS

fly

1.29

flies

1.11

hawk

0.96

bone

0.91

Fly

0.90

zilla

0.84

flight

0.83

 dragons

0.82

lance

0.81

fruit

0.80

Activations Density 0.021%

mentions of the television show "Dragon Ball Super"

occurrences of the word "Dragon" related to the context of the "Dragon Ball Super" series

No Comments

No Known Activations