INDEX

Explanations

positive adjectives related to size or extent

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of increase or enhancement

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

imer

-0.72

tags

-0.71

chin

-0.69

©¶æ

-0.68

wine

-0.66

pe

-0.66

Top

-0.64

wat

-0.64

TING

-0.64

 Built

-0.63

POSITIVE LOGITS

 likelihood

1.26

 flexibility

1.16

 distances

1.15

 reliance

1.14

 importance

1.12

 prominence

1.12

 quantities

1.11

 quantity

1.10

 sophistication

1.09

 amounts

1.08

Activations Density 0.078%

positive adjectives related to size or extent

phrases emphasizing the concept of increase or enhancement

No Comments

No Known Activations