INDEX

Explanations

words related to historical events and figures

oai_token-act-pair · gpt-3.5-turbo

historical figures and their actions

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

 depends

-0.69

ggle

-0.66

 continues

-0.61

)?

-0.60

 VIDEOS

-0.58

 partName

-0.57

":["

-0.57

'?

-0.56

gencies

-0.56

)!

-0.55

POSITIVE LOGITS

"'

0.63

"[

0.59

okingly

0.57

 aborted

0.52

 eighty

0.51

 Hitler

0.51

utm

0.51

 Nazi

0.50

 ninety

0.50

 forty

0.48

Activations Density 2.347%

words related to historical events and figures

historical figures and their actions

No Comments

No Known Activations