INDEX

Explanations

the brand name "Hilton."

oai_token-act-pair · gpt-4-turbo

references to locations or entities with the word "Hilton" in them

oai_token-act-pair · gpt-3.5-turbo

mentions of the Hilton brand

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

*/(

-0.88

 redistributed

-0.75

anwhile

-0.75

FTWARE

-0.71

period

-0.71

atically

-0.68

 Izan

-0.67

reenshots

-0.66

umbnail

-0.66

osion

-0.65

POSITIVE LOGITS

 Hilton

1.14

 Hotel

0.97

 Marriott

0.89

 Coliseum

0.87

sburg

0.86

 hotels

0.76

 Plaza

0.73

 hotel

0.73

ilton

0.69

Activations Density 0.003%

the brand name "Hilton."

references to locations or entities with the word "Hilton" in them

mentions of the Hilton brand

No Comments

No Known Activations