INDEX

Explanations

mentions of and discussions around the concept of 'fake news'

oai_token-act-pair · gpt-3.5-turbo

tokens indicating the end of a text or section

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

Dialogue

-0.63

alties

-0.62

 ãĢĮ

-0.60

rises

-0.59

KR

-0.59

AAF

-0.59

 Leilan

-0.58

 Keller

-0.57

essage

-0.56

immer

-0.56

POSITIVE LOGITS

usterity

0.97

tenance

0.94

0.87

`,

0.86

Â»

0.83

terday

0.83

\)

0.82

"!

0.82

'?

0.81

/,

0.80

Activations Density 0.308%

mentions of and discussions around the concept of 'fake news'

tokens indicating the end of a text or section

No Comments

No Known Activations