INDEX

Explanations

academic titles and names with specific characteristics

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to individuals or research subjects

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

 Craigslist

-0.75

 Vanity

-0.71

 Oath

-0.68

aepernick

-0.68

Offline

-0.68

 Daddy

-0.67

 TRUMP

-0.67

 Celebration

-0.66

 Exile

-0.66

VERTISEMENT

-0.65

POSITIVE LOGITS

 hypothes

1.34

 hypothesized

1.26

et

1.20

 resear

1.20

 studied

1.19

 analysed

1.16

 calculates

1.08

 researchers

1.07

 explains

1.07

 suggests

1.07

Activations Density 0.212%

academic titles and names with specific characteristics

proper nouns related to individuals or research subjects

No Comments

No Known Activations