INDEX

Explanations

phrases related to rankings or levels of superiority

oai_token-act-pair · gpt-3.5-turbo

phrases related to rankings or tiers within competitive contexts

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

 Sawyer

-0.71

 Imran

-0.68

Dia

-0.65

 Diary

-0.63

 Stranger

-0.62

 Cumm

-0.61

 Cavern

-0.60

 benefic

-0.60

Cry

-0.60

Äĩ

-0.60

POSITIVE LOGITS

level

1.33

sized

1.27

tier

1.22

class

1.12

ranking

1.12

rank

1.07

selling

1.03

eyed

1.03

ranked

1.02

heavy

1.02

Activations Density 0.078%

phrases related to rankings or levels of superiority

phrases related to rankings or tiers within competitive contexts

No Comments

No Known Activations