INDEX

Explanations

phrases indicating frequency or likelihood of occurrence

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-0.94

 ProtoMessage

-0.75

Diweddarwch

-0.75

]();

-0.74

بوابة

-0.73

 Raoul

-0.70

 scratch

-0.67

"]=

-0.65

cences

-0.64

 spit

-0.63

POSITIVE LOGITS

MOST

0.67

我最

0.65

 ExecuteAsync

0.65

ăț

0.62

most

0.62

 MOST

0.61

BEST

0.61

DataBind

0.61

 ISNI

0.59

 piú

0.59

Activations Density 0.125%

phrases indicating frequency or likelihood of occurrence

No Comments

No Known Activations