INDEX

Explanations

phrases related to public exhibitions or demonstrations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "display" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

trak

-0.74

istani

-0.73

owsky

-0.66

allo

-0.65

pool

-0.64

oner

-0.64

 breathed

-0.63

lake

-0.63

ceans

-0.61

SOURCE

-0.61

POSITIVE LOGITS

 displays

1.18

 prominently

0.99

 display

0.98

 Thumbnails

0.93

 exhibits

0.90

 banners

0.87

wcsstore

0.84

Display

0.84

display

0.81

 Display

0.79

Activations Density 0.013%

phrases related to public exhibitions or demonstrations

occurrences of the word "display" in various contexts

No Comments

No Known Activations