INDEX

Explanations

phrases related to news and events

oai_token-act-pair · gpt-3.5-turbo

references to significant events or discussions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anwhile

-0.88

srf

-0.69

 Antar

-0.58

 respectively

-0.58

.'"

-0.54

'."

-0.54

é¾įåĸļå£«

-0.53

-0.52

).[

-0.50

hiba

-0.50

POSITIVE LOGITS

 hindsight

0.55

pires

0.49

 outweigh

0.48

âĢ¦)

0.47

 debacle

0.47

itar

0.46

Reviewer

0.46

papers

0.45

Luck

0.45

 weddings

0.44

Activations Density 1.921%

phrases related to news and events

references to significant events or discussions

No Comments

No Known Activations