INDEX

Explanations

phrases containing the word "no" in the context of making a decision or statement

oai_token-act-pair · gpt-3.5-turbo

negative expressions or phrases related to absence or prohibition

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

amiya

-0.74

regor

-0.68

Voy

-0.65

 trave

-0.65

endar

-0.65

 Halls

-0.63

ulty

-0.62

allery

-0.62

 Challenges

-0.62

)=(

-0.61

POSITIVE LOGITS

xious

1.11

obs

0.81

âĢĳ

0.76

anium

0.72

uter

0.72

osphere

0.71

brainer

0.71

isons

0.65

except

0.65

umen

0.65

Activations Density 0.035%

phrases containing the word "no" in the context of making a decision or statement

negative expressions or phrases related to absence or prohibition

No Comments

No Known Activations