INDEX

Explanations

instances where the word "slide" is mentioned along with related terms

oai_token-act-pair · gpt-3.5-turbo

references to slides in presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¯ãĥ³

-0.74

omes

-0.73

orate

-0.73

Interstitial

-0.72

raising

-0.72

joice

-0.70

ilee

-0.70

elf

-0.69

etheless

-0.69

 Carbuncle

-0.69

POSITIVE LOGITS

 slides

0.91

 slide

0.90

 Canaver

0.88

itzer

0.83

creen

0.80

uten

0.75

hare

0.74

 Slide

0.72

ideshow

0.72

 slope

0.71

Activations Density 0.025%

instances where the word "slide" is mentioned along with related terms

references to slides in presentations

No Comments

No Known Activations