INDEX

Explanations

phrases indicating encouragement or urgency

oai_token-act-pair · gpt-3.5-turbo

expressions of exasperation and rhetorical questioning

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

isk

-0.63

ãĤ±

-0.62

isen

-0.61

 sled

-0.61

 roots

-0.60

Prev

-0.58

CV

-0.58

itory

-0.58

lishes

-0.57

Els

-0.57

POSITIVE LOGITS

Lah

0.73

 thou

0.68

 pity

0.68

Gaw

0.67

 Anyway

0.67

 Jinn

0.67

ĳå£«

0.65

 Beware

0.63

 beware

0.62

 Defender

0.62

Activations Density 0.420%

phrases indicating encouragement or urgency

expressions of exasperation and rhetorical questioning

No Comments

No Known Activations