INDEX

Explanations

instances where the word "add" is used in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the concept of addition or adding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

zee

-0.66

yah

-0.65

doi

-0.64

bis

-0.64

spread

-0.63

Present

-0.61

kat

-0.61

Interested

-0.61

 Alone

-0.60

NING

-0.60

POSITIVE LOGITS

endum

1.31

 insult

1.19

ictions

1.09

ition

0.99

 thereto

0.97

itions

0.96

itional

0.95

ictive

0.93

ressing

0.90

icts

0.89

Activations Density 0.061%

instances where the word "add" is used in various contexts

references to the concept of addition or adding elements

No Comments

No Known Activations