INDEX

Explanations

phrases indicating ethical judgments or considerations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating moral evaluations or judgments

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

quickShipAvailable

-0.69

Orig

-0.61

;;;;;;;;

-0.60

uli

-0.60

ById

-0.58

 benefiting

-0.56

riot

-0.56

 Oops

-0.56

 dilig

-0.56

 Ended

-0.56

POSITIVE LOGITS

 visualize

0.84

adies

0.81

 practise

0.79

 avoid

0.79

ads

0.78

 automate

0.77

ggles

0.76

 accomplish

0.76

 convince

0.75

wered

0.75

Activations Density 0.127%

phrases indicating ethical judgments or considerations

phrases indicating moral evaluations or judgments

No Comments

No Known Activations