INDEX

Explanations

references related to the television series Game of Thrones

oai_token-act-pair · gpt-3.5-turbo

references to the television series "Game of Thrones."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

trak

-0.89

iating

-0.73

ntil

-0.71

esville

-0.71

igating

-0.71

ees

-0.70

Trend

-0.68

aneous

-0.68

aneously

-0.67

xon

-0.65

POSITIVE LOGITS

 Thrones

1.36

 Lann

1.22

 Reborn

0.82

 Targ

0.80

 compr

0.79

acters

0.79

RM

0.78

 Dracula

0.77

 premiered

0.72

 novels

0.71

Activations Density 0.025%

references related to the television series Game of Thrones

references to the television series "Game of Thrones."

No Comments

No Known Activations