INDEX

Explanations

mentions of specific episodes in a TV series

oai_token-act-pair · gpt-3.5-turbo

references to specific episodes in a series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

forts

-0.78

lying

-0.70

paces

-0.64

 CONS

-0.63

minist

-0.62

isse

-0.62

helm

-0.62

ror

-0.61

bos

-0.61

RO

-0.60

POSITIVE LOGITS

 episode

3.63

episode

2.61

 episodes

2.58

 Episode

2.35

Episode

2.15

isode

1.66

isodes

1.62

 chapter

1.45

 installment

1.33

 podcast

1.33

Activations Density 0.014%

mentions of specific episodes in a TV series

references to specific episodes in a series

No Comments

No Known Activations