INDEX

Explanations

phrases related to questioning or uncertain statements

oai_token-act-pair · gpt-3.5-turbo

phrases related to responsibility and blame

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Tut

-0.57

 Milton

-0.51

 Muss

-0.51

 Admission

-0.50

 Mechdragon

-0.50

 Keynes

-0.49

Umb

-0.48

NEC

-0.48

 Commodore

-0.48

Tud

-0.48

POSITIVE LOGITS

laughs

0.73

*/(

0.71

è¦ļéĨĴ

0.70

ymes

0.66

É

0.64

Laughs

0.62

cember

0.62

ngth

0.58

INO

0.58

_(

0.57

Activations Density 2.063%

phrases related to questioning or uncertain statements

phrases related to responsibility and blame

No Comments

No Known Activations