INDEX

Explanations

web-related terms and actions related to website interaction

oai_token-act-pair · gpt-3.5-turbo

references to user interactions and behaviors on websites or platforms

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

 Disaster

-0.71

 Immunity

-0.69

 assass

-0.68

 Rhodes

-0.67

 slander

-0.67

 miracle

-0.66

 miracles

-0.66

 tragedies

-0.65

fug

-0.65

 ashes

-0.64

POSITIVE LOGITS

 liking

1.12

 purchasing

1.10

 browsing

1.03

 craving

1.02

 buying

1.00

 dissatisfied

0.97

umers

0.97

 subscribing

0.93

 purchases

0.93

 consume

0.93

Activations Density 0.564%

web-related terms and actions related to website interaction

references to user interactions and behaviors on websites or platforms

No Comments

No Known Activations