INDEX

Explanations

phrases indicating absence or lack of something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the absence or lack of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

athe

-0.76

lio

-0.70

Bloomberg

-0.68

rex

-0.68

Quote

-0.68

cold

-0.67

ean

-0.66

vantage

-0.66

ontent

-0.66

aly

-0.66

POSITIVE LOGITS

 discern

1.17

 shortage

1.12

xious

1.05

 guarantee

1.02

 detectable

1.01

 guarantees

1.00

 indication

0.99

 obvious

0.99

 apparent

0.96

 conceivable

0.94

Activations Density 0.082%

phrases indicating absence or lack of something

phrases indicating the absence or lack of something

No Comments

No Known Activations