INDEX

Explanations

phrases indicating a certainty or conclusive statement

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

iliated

-0.66

ourses

-0.63

 seiz

-0.63

 confir

-0.62

ourse

-0.61

pread

-0.61

 tremend

-0.60

 undermin

-0.59

etheus

-0.58

illary

-0.57

POSITIVE LOGITS

;)

0.95

 ðŁĺ

0.79

:)

0.78

:-)

0.78

 haha

0.78

âĢ¦)

0.75

 ðŁĻĤ

0.75

âĢ¦.

0.73

?!

0.71

Activations Density 0.231%

phrases indicating a certainty or conclusive statement

phrases indicating uncertainty or questioning

No Comments

No Known Activations