INDEX

Explanations

adjectives describing degree or intensity

oai_token-act-pair · gpt-3.5-turbo

quantifiers and modifiers that indicate degree or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 IMAGES

-0.92

 VIDEOS

-0.84

each

-0.70

 Packs

-0.70

çīĪ

-0.69

ggles

-0.68

ilers

-0.67

 earns

-0.67

doms

-0.66

 executes

-0.66

POSITIVE LOGITS

 reliant

0.80

 unlikely

0.80

 proud

0.78

 fortunate

0.77

 aware

0.77

done

0.77

 insensitive

0.75

 honoured

0.75

 allergic

0.74

 honored

0.74

Activations Density 0.324%

adjectives describing degree or intensity

quantifiers and modifiers that indicate degree or extent

No Comments

No Known Activations