INDEX

Explanations

opinions or arguments, sometimes related to legal matters or ethical issues

oai_token-act-pair · gpt-3.5-turbo

significant numerical data and related contexts in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 endif

-0.75

 accordingly

-0.62

".[

-0.60

".

-0.58

."[

-0.58

 TAMADRA

-0.58

.ï¿½

-0.56

"/>

-0.56

.''.

-0.55

 nonetheless

-0.55

POSITIVE LOGITS

iatus

0.54

Ĭ±

0.51

ovember

0.49

è£ħ

0.49

aughs

0.48

ilings

0.48

otomy

0.48

iosity

0.45

anity

0.45

 sequ

0.44

Activations Density 1.687%

opinions or arguments, sometimes related to legal matters or ethical issues

significant numerical data and related contexts in a document

No Comments

No Known Activations