INDEX

Explanations

words related to potential danger or serious consequences

oai_token-act-pair · gpt-3.5-turbo

occurrences of empty or null tokens

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

 disadvant

-0.64

 Vaugh

-0.64

 undermin

-0.60

 thous

-0.59

atever

-0.56

 predec

-0.55

 challeng

-0.52

Tokens

-0.49

 advoc

-0.49

'."

-0.48

POSITIVE LOGITS

\":

0.56

Â¶

0.56

!:

0.54

 Xperia

0.51

':

0.49

 OnePlus

0.48

 âĢº

0.48

 partName

0.48

ARM

0.47

âĦ¢:

0.44

Activations Density 0.787%

words related to potential danger or serious consequences

occurrences of empty or null tokens

No Comments

No Known Activations