INDEX

Explanations

questions or statements expressing curiosity about future outcomes

oai_token-act-pair · gpt-3.5-turbo

questions and phrases expressing curiosity about future events or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

arest

-0.68

GV

-0.66

 WATCHED

-0.65

ansom

-0.65

 cautioned

-0.63

question

-0.63

ashington

-0.63

 guiActiveUn

-0.62

 Nonetheless

-0.61

stated

-0.61

POSITIVE LOGITS

 happens

1.02

 unfolds

0.85

 develops

0.83

 shenanigans

0.83

 pops

0.81

 others

0.74

 pans

0.73

 else

0.73

 reactions

0.70

 happen

0.70

Activations Density 0.071%

questions or statements expressing curiosity about future outcomes

questions and phrases expressing curiosity about future events or outcomes

No Comments

No Known Activations