INDEX

Explanations

image-related content and references in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

JsonProperty

-0.75

 שוליים

-0.75

:✨

-0.73

 дописавши

-0.72

 Biôgrafia

-0.69

canestro

-0.69

 متعلقه

-0.69

">//

-0.69

Népesség

-0.69

存于互联网档案馆

-0.67

POSITIVE LOGITS

?[

2.19

?(

0.89

?\

0.86

*[

0.76

![

0.74

.[

0.68

?&

0.67

?$

0.67

?\\

0.66

?…

0.65

Activations Density 0.045%

image-related content and references in the document

No Comments

No Known Activations