INDEX

Explanations

numerical values in various contexts

oai_token-act-pair · gpt-3.5-turbo

data related to statistics and numerical information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

requently

-0.64

inventoryQuantity

-0.60

 alot

-0.58

channelAvailability

-0.53

 usual

-0.51

 tremend

-0.50

 favourites

-0.49

 Whilst

-0.49

 lately

-0.49

liest

-0.49

POSITIVE LOGITS

âĢ

0.77

âĢ¢âĢ¢

0.75

 ÂŃ

0.66

 âĢ

0.65

—

0.55

Ì

0.55

â

0.55

Â·Â·

0.52

___

0.52

——

0.50

Activations Density 1.131%

numerical values in various contexts

data related to statistics and numerical information

No Comments

No Known Activations