INDEX

Explanations

phrases related to historical events and scholarly discourse

oai_token-act-pair · gpt-3.5-turbo

references to historical events or figures

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

 surgeries

-0.60

 perimeter

-0.60

isSpecialOrderable

-0.56

 goodwill

-0.52

FILE

-0.50

patient

-0.50

 broom

-0.50

SHARE

-0.48

wives

-0.48

 stret

-0.48

POSITIVE LOGITS

 aptly

0.75

 quoting

0.72

 "âĢ¦

0.63

""

0.61

"[

0.58

 "...

0.58

 sarcast

0.56

Rue

0.56

 distribut

0.55

vertisement

0.54

Activations Density 0.715%

phrases related to historical events and scholarly discourse

references to historical events or figures

No Comments

No Known Activations