INDEX

Explanations

actions and activities associated with notable figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 själva

-0.41

ODO

-0.40

 zeich

-0.39

괄

-0.39

 kaarangay

-0.39

uns

-0.38

owohl

-0.38

 peck

-0.38

);"

-0.38

 ")";

-0.37

POSITIVE LOGITS

 незавершена

0.90

principalColumn

0.76

 himself

0.74

 متعلقه

0.73

المناصب

0.71

 ModelExpression

0.67

+#+

0.67

ngdoc

0.65

 herself

0.64

 الحره

0.64

Activations Density 0.587%

actions and activities associated with notable figures and events

No Comments

No Known Activations