INDEX

Explanations

phrases indicating causality or reason

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causality or reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

orem

-0.74

ahs

-0.68

enaries

-0.68

called

-0.67

orously

-0.66

ona

-0.64

interrupted

-0.63

raining

-0.62

inant

-0.62

thread

-0.62

POSITIVE LOGITS

 considering

0.76

}:

0.73

 Especially

0.71

 behold

0.70

assetsadobe

0.70

 suppose

0.69

 suffice

0.68

 imagine

0.65

 Mint

0.65

imaru

0.60

Activations Density 0.682%

phrases indicating causality or reason

phrases that indicate causality or reasoning

No Comments

No Known Activations