INDEX

Explanations

phrases implying a continuous increase in intensity or activity

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a trend of increasing behaviors or emotions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ãĤ¨ãĥ«

-0.75

hra

-0.73

glers

-0.72

pring

-0.70

oops

-0.70

 Whip

-0.70

iversary

-0.68

ENA

-0.68

rats

-0.67

pta

-0.66

POSITIVE LOGITS

 sophisticated

1.00

 reliant

0.98

 frustrated

0.96

 prevalent

0.93

 polarized

0.89

 agitated

0.88

 erratic

0.88

 desperate

0.88

 adept

0.87

 embold

0.86

Activations Density 0.070%

phrases implying a continuous increase in intensity or activity

phrases indicating a trend of increasing behaviors or emotions

No Known Activations