INDEX

Explanations

phrases related to specific actions or events

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to various types of applications or significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Haram

-0.64

 Hots

-0.63

 Flavoring

-0.63

 Important

-0.61

 Answer

-0.57

 Pist

-0.56

iatus

-0.56

 Quote

-0.56

 Conclusion

-0.55

BIP

-0.55

POSITIVE LOGITS

lessly

0.84

less

0.81

able

0.79

ably

0.72

 lounge

0.69

rooms

0.68

boards

0.67

room

0.67

ware

0.67

abal

0.66

Activations Density 0.848%

phrases related to specific actions or events

words and phrases related to various types of applications or significant events

No Comments

No Known Activations