INDEX

Explanations

temperature values in degrees

oai_token-act-pair · gpt-3.5-turbo

temperatures expressed in degrees Celsius and Fahrenheit

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

 Saga

-0.76

ardless

-0.74

ortment

-0.74

gotten

-0.74

abor

-0.73

etsk

-0.73

erc

-0.71

eson

-0.69

 purse

-0.67

ulations

-0.67

POSITIVE LOGITS

Âº

1.17

Â°

1.14

º

1.03

 Fahrenheit

0.92

 Celsius

0.92

elsius

0.91

âĶĢâĶĢâĶĢâĶĢ

0.83

Temperature

0.80

³

0.80

¿

0.76

Activations Density 0.005%

temperature values in degrees

temperatures expressed in degrees Celsius and Fahrenheit

No Comments

No Known Activations