INDEX

Explanations

dates related to specific months and years

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.49

âķĲâķĲ

-0.44

Â¶

-0.43

 lapt

-0.42

âķĲ

-0.41

 Berman

-0.41

[_

-0.41

channelAvailability

-0.40

ß

-0.40

Pwr

-0.40

POSITIVE LOGITS

ibl

0.42

imon

0.37

uper

0.36

rament

0.36

ibur

0.35

ilater

0.35

 comprom

0.35

bye

0.35

quila

0.34

 choke

0.34

Activations Density 6.101%

dates related to specific months and years

No Comments

No Known Activations