INDEX

Explanations

proper nouns and associated details

oai_token-act-pair · gpt-3.5-turbo

entities and organizations involved in various sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

"!

-0.67

!".

-0.65

".

-0.62

".[

-0.60

$.

-0.60

 inev

-0.59

".

-0.57

Spread

-0.57

."

-0.53

 ransom

-0.53

POSITIVE LOGITS

 meanwhile

0.58

 spokesman

0.58

 spokeswoman

0.56

 Lauder

0.55

 Tiff

0.51

quartered

0.51

Ala

0.50

 declined

0.50

Lor

0.48

 Upper

0.48

Activations Density 1.118%

proper nouns and associated details

entities and organizations involved in various sectors

No Comments

No Known Activations