INDEX

Explanations

instances of advice or instruction

oai_token-act-pair · gpt-3.5-turbo

phrases related to social behavior and responsibility

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

>>>>>>>>

-0.56

Pwr

-0.54

----------------------------------------------------------------

-0.52

nsic

-0.52

voy

-0.51

 å¤

-0.50

 Medline

-0.50

================================

-0.49

=-=-

-0.49

Yon

-0.48

POSITIVE LOGITS

 interacted

0.63

 desired

0.63

 deems

0.59

 metic

0.59

heit

0.59

 deem

0.57

 interact

0.57

ufact

0.55

 actually

0.55

 transitioned

0.55

Activations Density 0.799%

instances of advice or instruction

phrases related to social behavior and responsibility

No Comments

No Known Activations