INDEX

Explanations

expressions of gratitude or acknowledgments

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude or appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Nanto

-0.60

 Anth

-0.57

 behavi

-0.54

ually

-0.52

 envis

-0.51

 magnets

-0.51

ways

-0.51

erent

-0.51

 neighb

-0.51

 envy

-0.51

POSITIVE LOGITS

giving

0.68

interstitial

0.64

à¤¾

0.61

monary

0.61

LOCK

0.58

govtrack

0.57

advertisement

0.57

wcsstore

0.57

BRE

0.57

opus

0.53

Activations Density 0.009%

expressions of gratitude or acknowledgments

expressions of gratitude or appreciation

No Comments

No Known Activations