INDEX

Explanations

references to categorical organization or classification in the content

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

الدراسه

-0.75

 endfor

-0.73

DockStyle

-0.70

Portail

-0.68

lahraga

-0.67

 Shakspeare

-0.66

randomUUID

-0.65

GEBURTS

-0.65

mappedBy

-0.64

̍t

-0.63

POSITIVE LOGITS

 Wikimédia

0.51

raja

0.47

 berta

0.45

रण

0.45

kij

0.44

 Firstly

0.44

定

0.44

 sever

0.44

共

0.42

 ways

0.41

Activations Density 0.419%

references to categorical organization or classification in the content

No Comments

No Known Activations