INDEX

Explanations

mentions of the Department of Energy (DE)

oai_token-act-pair · gpt-3.5-turbo

instances of the abbreviation "DE" in various 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

ocene

-0.88

imity

-0.81

olulu

-0.80

 BaseType

-0.78

toggle

-0.77

oulos

-0.77

ãĤ¤ãĥĪ

-0.75

andise

-0.73

ãĥĥãĤ¯

-0.72

 è£ıè¦ļéĨĴ

-0.72

POSITIVE LOGITS

FAULT

1.21

VICE

1.19

FIN

1.12

POS

1.03

FINE

0.95

VEL

0.94

PUT

0.90

ATH

0.87

leted

0.86

PORT

0.85

Activations Density 0.012%

mentions of the Department of Energy (DE)

instances of the abbreviation "DE" in various contexts

No Comments

No Known Activations