INDEX

Explanations

urgent calls to action or important information

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate must-watch content or urgent recommendations

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

 Entered

-0.74

bill

-0.51

 arche

-0.51

 Wilderness

-0.50

 Burton

-0.50

 Letter

-0.49

Haz

-0.48

wcs

-0.48

 Construct

-0.48

POSITIVE LOGITS

rgb

0.73

 itself

0.67

ohm

0.66

ynasty

0.64

yssey

0.61

yip

0.61

ļé

0.61

rylic

0.58

eport

0.58

sson

0.58

Activations Density 1.837%

urgent calls to action or important information

phrases that indicate must-watch content or urgent recommendations

No Comments

No Known Activations