INDEX

Explanations

phrases related to sharing updates and commentary in a casual style

oai_token-act-pair · gpt-3.5-turbo

statements reflecting self-awareness and personal opinions

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

).[

-0.65

."[

-0.60

anwhile

-0.60

 therefore

-0.58

]."

-0.58

.'"

-0.55

)."

-0.55

'."

-0.53

".[

-0.52

.""

-0.51

POSITIVE LOGITS

Spoiler

0.63

 spoilers

0.60

 Spoiler

0.59

 FANTASY

0.57

 lovely

0.57

 Patreon

0.57

 spoiler

0.56

 COMPLE

0.53

 REALLY

0.53

Reviewer

0.52

Activations Density 3.015%

phrases related to sharing updates and commentary in a casual style

statements reflecting self-awareness and personal opinions

No Comments

No Known Activations