INDEX

Explanations

superlatives and comparative phrases

oai_token-act-pair · gpt-3.5-turbo

superlative phrases that emphasize importance or significance

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

 Directions

-0.69

Yeah

-0.69

umed

-0.68

leys

-0.67

 Yeah

-0.67

 Kills

-0.64

amber

-0.64

 Daly

-0.63

lings

-0.63

 Grants

-0.62

POSITIVE LOGITS

 overlooked

0.78

 encaps

0.77

 illuminating

0.72

 seminal

0.71

 underrated

0.71

ointed

0.71

 distingu

0.70

 fitting

0.70

 noteworthy

0.70

 notable

0.69

Activations Density 0.076%

superlatives and comparative phrases

superlative phrases that emphasize importance or significance

No Comments

No Known Activations