INDEX

Explanations

phrases indicating changes in regulations or policies, particularly those related to business or technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Lähteet

-0.73

Efq

-0.69

IBarButtonItem

-0.68

)++;

-0.67

tagHelperRunner

-0.66

"],

-0.66

 photolibrary

-0.65

født

-0.64

!")

-0.63

AutoresizingMask

-0.63

POSITIVE LOGITS

 includes

0.95

 including

0.81

includes

0.80

 include

0.75

 termasuk

0.73

 incluyen

0.69

 Including

0.69

 khususnya

0.68

including

0.67

 incluye

0.67

Activations Density 0.531%

phrases indicating changes in regulations or policies, particularly those related to business or technology

No Comments

No Known Activations