INDEX

Explanations

timestamps in a consistent format

oai_token-act-pair · gpt-3.5-turbo

content related to statistics or numerical information

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

etheless

-0.80

 Fisheries

-0.68

rays

-0.68

ĸļ

-0.67

 submar

-0.64

 slashing

-0.63

 throwing

-0.63

 watering

-0.63

hement

-0.61

xual

-0.60

POSITIVE LOGITS

CHAPTER

0.89

ccording

0.89

Posted

0.88

Author

0.88

Follow

0.84

robe

0.84

ÂłÂłÂłÂł

0.83

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.83

Anonymous

0.83

EGIN

0.82

Activations Density 0.123%

timestamps in a consistent format

content related to statistics or numerical information

No Comments

No Known Activations