INDEX

Explanations

sentences summarizing or pointing out key information in a text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

azo

-0.69

 Reward

-0.69

phans

-0.68

 Delivery

-0.68

 externalToEVAOnly

-0.66

 Valentine

-0.65

 Delay

-0.63

ickle

-0.63

 Competition

-0.63

bath

-0.63

POSITIVE LOGITS

 conclusions

1.33

 viewpoints

1.26

 pertinent

1.22

 factual

1.20

 opinions

1.14

 facts

1.13

 inaccur

1.11

 relevant

1.07

 misconceptions

1.07

 perspectives

1.06

Activations Density 0.705%

sentences summarizing or pointing out key information in a text

No Comments

No Known Activations