INDEX

Explanations

references to financial amounts in euros

oai_token-act-pair · gpt-3.5-turbo

references to monetary amounts in euros

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

 Siber

-0.76

eer

-0.72

ITNESS

-0.69

Peb

-0.68

ĪĴ

-0.68

LESS

-0.66

 Sioux

-0.65

 Behavior

-0.64

 Doodle

-0.64

ļé

-0.63

POSITIVE LOGITS

 (Â£

1.06

($

0.96

âĤ¬

0.91

 âĤ¬

0.89

akis

0.84

 euros

0.81

kas

0.76

 apiece

0.76

imeter

0.75

illion

0.75

Activations Density 0.011%

references to financial amounts in euros

references to monetary amounts in euros

No Comments

No Known Activations